Qoder CLI

# Fix list: Qoder CLI

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/qoder-cli, the October 2026 research run, assessed 18 October 2026. Grade C, 59.3 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Qoder CLI: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 51 out of 100, up to 9.8 more on the total

Why it scored 51: Local-package reading, the same as the other closed-source harnesses. An install script for macOS, Linux and Windows on arm64 and amd64 that checks a SHA-256 from a manifest on the same download host, and an npm package with Node.js 20 or later stated (20). No public CI or test suite, since no source is published (0). We found no public issue tracker for the CLI. The forum's bug-reports category, shared by every Qoder product, had 116 new topics in the month to 18 October, and 15 of the 29 topics on its first page had no reply. A few named the CLI (8). Versions are semver-shaped and every release is dated in the release notes, but removals such as `/goal take` in 1.1.11 shipped in patch versions without a breaking-change label (8). 1.0.0 on 20 May 2026, now 1.1.73 (15). 20+0+8+8+15 = 51.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: Harness reading of the published rubric, scored on the Qoder subscription the CLI needs. No payment protocol (0). Plan prices, the Credit Pack price ($20 for 1,500 credits) and per-model credit factors are public in the docs without a login. qoder.com/pricing is disallowed by robots.txt and wasn't read (20). A Free plan with basic models for a limited number of messages and a 14-day Pro trial with 300 credits. We found no statement on whether a card is needed (15). A person signs in through a browser, and a PAT is created by hand at qoder.com/account/integrations (0). 0+20+15+0 = 35.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 3. Security & auth, 55 out of 100, up to 7.9 more on the total

Why it scored 55: Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Browser sign-in with background refresh, or a PAT created with chosen permissions and an expiry and revocable, plus scoped service accounts for organisations. Usage statistics and AI code statistics are on by default with documented opt-outs, and the privacy policy lets users turn off Share & Improve depending on the plan, without saying which plans or the default (18). Five permission modes, deny over ask over allow across seven rule layers, ask turned into deny in headless runs, a `dont_ask` mode, trusted directories, protected paths and an administrator switch that disables YOLO. No local sandbox is documented, and `auto` mode lets an AI classifier decide and approves read-only tools on any path (14). Workspace files can't add auto-mode rules, protected paths stop the agent changing shell startup files or .mcp.json without approval, and network paths always ask on Windows. A project's .qoder/settings.json is still one of the rule layers, and nothing contains a command once approved (9). The enterprise audit log records administrative and configuration events for administrators and says it leaves out prompts, terminal commands, MCP call parameters and CLI execution, and individuals have local session history only (5). qoder.com/enterprise says Qoder is certified to ISO/IEC 27001 and has completed a SOC 2 Type II audit. No security.txt, disclosure policy or bug bounty was found, and fixes appear as one-line release notes without advisories (9). 18+14+9+5+9 = 55.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 80 out of 100, up to 3.3 more on the total

Why it scored 80: Framework reading, adapted to a harness driven by a pipeline. `--tools`, `--allowed-tools` and `--disallowed-tools` restrict built-in tools, and `--strict-mcp-config` with `--allowed-mcp-server-names` limits MCP servers. Nothing on deferred MCP tool loading was found (18). text, json and stream-json output, `--max-turns`, `--max-output-tokens` and `--no-session-persistence` (16). Distinct exit codes for authentication, input, configuration, turn-limit and tool failures, and SDK Result subtypes with error codes (16). `--continue`, `--resume`, `--session-id`, `--fork-session`, SDK checkpoints with rewind, and `--max-model-request-retries` (15). Official SDKs in TypeScript and Python, an ACP server, and headless runs that need only a PAT and a permission flag (15). 18+16+16+15+15 = 80.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Transparency & trust, 64 out of 100, up to 3.2 more on the total

Made of editorial 51, provenance 76.

Why it scored 64: Proprietary, with clear terms from BRIGHT ZENITH PRIVATE LIMITED under Singapore law, and the SDK's LICENSE points to the same terms (15). The privacy policy lists purposes with retention for each (mostly for as long as the account exists), names storage in the United States, Singapore and Japan and names model providers. The terms let the operator use User Content to improve the Services unless Share & Improve is turned off, and the policy says the opt-out depends on the plan. No subprocessor list or DPA was found (14). Dated notices with two weeks' warning for the Lite tier removal (4 to 18 September 2026) and for the credit factor change on 21 September, but no stated deprecation policy (8). Usage statistics and AI code statistics are disclosed as settings with an opt-out, both on by default, and the installer's telemetry isn't described (14). 15+14+8+14 = 51.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 81 out of 100, up to 3.1 more on the total

Why it scored 81: Framework reading. A CLI reference with types and defaults for every flag, a settings reference with types and defaults, TypeScript declaration files and a Python reference for the SDK, and Result and error-code tables. No schema for the stream-json events was found (16). docs.qoder.com/llms.txt indexes every page with a Markdown twin, and robots.txt allows both (10). The permissions page states what each mode does and is best for, what headless runs do with ask, and which actions skip the auto classifier (17). Permission modes and output formats are enums and rules have a fixed syntax (12). CI examples, an SDK error page with exit codes 0, 1, 41, 42, 44, 52, 53, 54 and 130, Result subtypes and a troubleshooting index. Code 44 names a sandbox the docs don't describe (14). Dated release notes for the CLI and the SDK, though the SDK notes stop at 1.0.41 on 15 September while npm has 1.0.53, and the CLI reference still names the removed `lite` model (12). 16+10+17+12+14+12 = 81.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Maintenance & community, 72 out of 100, up to 2.5 more on the total

Why it scored 72: 1.1.73 on 16 October 2026 (30). 74 dated CLI versions between 20 July and 16 October 2026 (20). No public issue tracker. A Discourse forum with bug-report and feature-request categories, where 15 of the 29 bug reports on the first page had no reply when read on 18 October (7). Current official SDKs, `@qoder-ai/qoder-agent-sdk` 1.0.53 on 15 October and `qoder-agent-sdk` 1.0.15 on PyPI on 23 September 2026 (12). No public CI. npm versions carry registry signatures and the install script checks a SHA-256 (3). 30+20+7+12+3 = 72.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-09-19. CLI 1.1.57 fixed "a security issue where internal Git calls could execute repository configuration commands", so opening an untrusted repository could run commands from its Git configuration. Fixed within the month and disclosed only as a release-note line, with no advisory, affected versions or CVE found. Inside six months, -2 (https://docs.qoder.com/release-notes/qoder-cli.md)
- 2026-07-16. CLI 1.0.47 fixed the PreToolUse hook not taking effect in headless and SDK modes. The permissions page describes that hook as an interception that holds even in YOLO mode, so headless and SDK runs before the fix skipped organisation hooks. Fixed and noted in the release notes. Judgement call, -1 (https://docs.qoder.com/release-notes/qoder-cli.md)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: qoder.com/pricing, which robots.txt disallows. Prices come from the docs pricing pages
- unchecked: whether a card is needed for the Free plan, and how many basic-model messages it allows
- unchecked: the default of Share & Improve on each individual plan. The privacy policy says the opt-out depends on the plan
- unchecked: GitHub, which the brief says refused requests, so any public repository, issues or advisories there weren't read
- Whether the CLI has a local sandbox. The SDK error page lists exit code 44 as a fatal sandbox error and no other page describes one
- What telemetry the install step sends. The install script says the binary's install subcommand handles telemetry
- Which versions were affected by the Git configuration fix in 1.1.57. No advisory was found
- The Agent SDK release notes stop at 1.0.41 (15 September 2026) while npm lists 1.0.53 (15 October 2026)

## Weaknesses

- No local sandbox is documented, and `auto` mode approves read-only tools on any path
- Usage and AI code statistics are on by default, and content use for improvement depends on the plan
- Closed source with no public CI, issue tracker or security advisories, and the audit log leaves out CLI execution
- No security.txt, disclosure policy or status page found
- Agent SDK release notes stop at 1.0.41 on 15 September while npm has 1.0.53

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Set `QODER_PERSONAL_ACCESS_TOKEN` in CI. The browser sign-in can't complete in a headless run
- Pass `--permission-mode` with `--allowed-tools` in headless runs. Every ask is denied, and `--yolo` removes all checks
- Set `--max-turns` on unattended runs, and branch on exit codes 41 (authentication) and 53 (turn limit)
- Set `privacy.usageStatisticsEnabled` and `aiCodeStatistics.enabled` to false in ~/.qoder/settings.json if usage data must stay local
- Don't pass `--model lite`. The Lite tier was removed on 18 September 2026 and headless requests naming it fail

## What the review panel asked for

- breaking-change labels
- current SDK release notes
- a per-request credit estimate before a run
- stream-json event schema
- document exit code 44
- advisories with affected versions
- vulnerability disclosure policy

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.