CLI Manager

# Fix list: CLI Manager

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/cli-manager, the October 2026 research run, assessed 14 October 2026. Grade B, 65.8 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 CLI Manager: 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. Security & auth, 58 out of 100, up to 7.4 more on the total

Why it scored 58: Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No telemetry or analytics found in the source. Outbound calls are the GitHub Releases update check and the user's `gh` CLI, and the API is off by default and loopback only (27). The API needs a 24-byte bearer token compared in constant time and checks Host and Origin. Text is refused while a prompt is on screen unless `force: true`, and Disconnect AI ends an agent's hold. Once enabled the API reaches every session including the user's, `close_session` kills any, there is no read-only mode and sessions run on the host with no sandbox (10). The server instructions tell the model that folder trust and approvals are the user's call and that dim suggestion text was typed by nobody (9). Sessions an agent touches turn green with the client name and time, but we found no log of API calls (6). No SECURITY.md, security.txt or bug bounty. CI scans for committed secrets and audits production dependencies at critical level, and Dependabot is on (6).

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.

## 2. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Read as local software. Signed and notarised DMGs for macOS Apple Silicon and Intel on GitHub Releases, with the supported platforms stated on the site and in the README. No package registry (20). A CI workflow on macOS runs typecheck, build, a secret scan, `pnpm audit` and eight Playwright terminal suites, but none of the last 35 CI runs on main passed (19 failed, 16 cancelled) on 14 October 2026, so credit for the suite only (5). No issue has ever been filed on GitHub. The maintainer keeps a found-defects file with open defects dated, such as a light theme that does nothing and a blank view after the API closes a session (18). Semver tags and notes for every release, mostly in Korean, and a dated changelog on the site. Breaking changes are not marked as such (10). Version 1.13.1, past 1.0 since 4 December 2025 (15).

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.

## 3. Agent ergonomics, 63 out of 100, up to 6 more on the total

Why it scored 63: 12 compact tools (15). `query` filters on workspaces and sessions, `scope` ai or all, and `lines` and `mode` screen or tail on reads, but no pagination on lists (16). Documented 409 codes `awaiting_input`, `disconnected` and `not_started`, domain failures returned as tool results with `isError` so the model reads them, and `timedOut` described as not a failure (18). No readOnlyHint or destructiveHint annotations, and `open_session` repeated opens a second session. Typing is refused while a question is on screen, which makes a blind retry safer (6). Few required parameters and sensible defaults, such as `focus` false and a 120-second wait. No SDK, only the `climanager-session` agent skill with a Node script (8).

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.

## 4. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy since v1.5.0 (20). No card or account (20). Download and enable the API with no signup (20). The paid Pro licence of versions 1.0 to 1.4 was removed on 8 April 2026, so there is no paid option to score.

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.

## 5. Transparency & trust, 54 out of 100, up to 4 more on the total

Made of editorial 57, provenance 50.

Why it scored 54: MIT in LICENSE and as detected by GitHub, while package.json still declares ISC (27). The privacy policy of 14 September 2026 covers the website (Google Analytics, feedback posts, download logs) and FAIR Social Ops, not the app. The site FAQ says the app sends no data externally, which the source we read agrees with (12). No deprecation policy. Dated release notes only (4). No telemetry found to disclose, and the FAQ says none is sent. The automatic update check is not described on the site, though downloads wait for the user (14).

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):

- Domain age: solhun.com, registered 2025-12-01 (under a year) (0 of 15)
- Terms of service: read, states 3 of the 7 things a reader expects (6.6 of 10)
- Privacy policy: read, states 3 of the 8 things a reader expects (6.3 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Maintenance & community, 62 out of 100, up to 3.3 more on the total

Why it scored 62: v1.13.1 on 13 October 2026 (30). Twelve releases since 17 August 2026 (20). No issues have been filed. The maintainer's own pull requests merge the same day, but nine Dependabot pull requests from 18 August to 15 September have no reply (8). Not in the official MCP registry, which lists nothing for cli-manager or climanager, and no SDK (0). Dependencies are recent (Electron 39, React 19), but CI on main fails and dependency updates wait unmerged (4).

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.

## 7. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: The MCP server lists 12 tools, each with a typed JSON Schema input and required fields marked. `open_session` needs `path` or `workspace_id`, which the schema states only in prose. No OpenAPI for the REST side (22). llms.txt at climanager.solhun.com (10). Tool descriptions and the server instructions state purpose and when not to act, for example focus only when the user asked and close only sessions the agent opened (18). Enums on `scope` and `mode`. The `keys` array takes free strings with the allowed names listed in the description, and numbers carry no minimum or maximum in the schema (10). curl examples, a status code table with what to do for each, and one `{ error: { code, message } }` shape (12). REST lives under `/v1`, with release notes and a site changelog (15).

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.

## 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.

- Judgement call. Listed in agent harnesses beside Paperclip, because it starts and drives Claude Code, Codex and Gemini CLI sessions for another agent. It does not run the model loop, so `agent.harness` is left out. The code category covers repositories and documentation, and the app's Git functions are not exposed through the API.
- The lead was right in substance. The 13 October 2026 Product Hunt launch is the product's second, and `firstReleased` is v1.0.0 on GitHub, 4 December 2025.
- We did not install or run the app. Every claim about behaviour comes from the source, the docs and the release notes.
- The README calls the app free and open source, and the site says MIT since v1.5.0. Whether the repository was public before April 2026 was not established.
- unchecked: rank or date of the first Product Hunt launch. Product Hunt says it launched in 2025 and the site cites #10 Product of the Day without a date.
- The licence file names woorichicken and 2024, the build config names LightSoft, the terms name solhun, and package.json says ISC.

## Weaknesses

- Once switched on, the API can read, type into and close every session in the app, including the user's own
- macOS only, and the API answers only while the desktop app is running and its window is alive
- None of the last 35 CI runs on the main branch passed, and nine Dependabot pull requests were open, the oldest from 18 August 2026
- No MCP tool annotations (readOnlyHint, destructiveHint) and no security policy or security.txt
- The privacy policy covers the website and another product, not the app

## 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.

- Ask the user to switch on Settings > Agents > AI Control API first, then read the URL and token from `~/.climanager/control-api.json`
- On `409 awaiting_input`, read the screen and answer with `keys` such as ["down","enter"]. Leave folder-trust and permission choices to the user
- Stop using a session on `409 disconnected`. The user took it back
- Treat `timedOut: true` from `wait` as still running, not as a failure, and wait again
- Pass `ephemeral: true` when opening a scratch or worktree folder, and close only sessions you opened

## 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.