Crush

# Fix list: Crush

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/crush, the October 2026 research run, assessed 18 October 2026. Grade C, 56.5 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 Crush: 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, 44 out of 100, up to 9.8 more on the total

Why it scored 44: 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. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names three opt-outs. The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, `permissions deny` hides tools and PreToolUse hooks can block calls. But `crush run` approves every permission request in its session automatically (internal/app/app.go), `--yolo` skips all prompts, and there's no sandbox, only a fixed refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's `.crushrc` and `$(...)` in `crush.json` run as code at startup, which the README warns about (3). Logs in `./.crush/logs/crush.log` with `crush logs`, sessions in a local database readable as JSON, and `crush stats`, with no OpenTelemetry export (9). The organisation's SECURITY.md gives an email address, CI runs CodeQL, Grype and govulncheck, releases are cosign-signed, and OSV (the GitHub Advisory Database's public mirror) and NVD list no vulnerability for Crush, rechecked in our GitHub record, which also finds no SECURITY.md in the repository. No security.txt and no bug bounty (10).

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, 54 out of 100, up to 9.2 more on the total

Why it scored 54: Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). A public build workflow runs `go test -race` on Linux, macOS and Windows for every push to main, over 314 test files, but GitHub pages and the API answered 403 so the current state is unconfirmed, and a 6 October commit fixed intermittent CI failures on all three platforms (17). 482 open and 828 closed issues, and 375 open against about 2,100 closed pull requests, per shields.io badge counts read on 18 October (our GitHub record). Over a third of all issues are still open, and how many are crashes or regressions, and how fast they're answered, couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of `crushrc` while still loading, and the config docs say not breaking the config API matters to the maintainers (7). v0.98.1, before 1.0, with no stability statement (0).

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, 52 out of 100, up to 7.8 more on the total

Why it scored 52: Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (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. Schema & documentation, 65 out of 100, up to 5.7 more on the total

Why it scored 65: Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).

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.

## 5. Payments & pricing, 55 out of 100, up to 5.6 more on the total

Why it scored 55: No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20).

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.

## 6. Transparency & trust, 56 out of 100, up to 3.9 more on the total

Made of editorial 49, provenance 63.

Why it scored 56: FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives three opt-outs, but doesn't mention the alias to the Hyper account (15).

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: charm.land, registered 2023-08-17 (3 years) (7 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 82 out of 100, up to 1.6 more on the total

Why it scored 82: v0.98.1 on 9 October 2026 on npm (30). 20 npm releases in the 90 days to 18 October, 0.86.0 to 0.98.1 (20). About 2,100 pull requests closed against 375 open, and 828 issues closed against 482 open, per shields.io badge counts read on 18 October (our GitHub record), with 514 commits in the 90 days to 18 October and new contributors signing the CLA most days. Reply times couldn't be read (12). No SDK, as with other harnesses. npm, Homebrew, Winget, Scoop, apt, yum and NUR builds track releases, and the latest npm version matches the latest tag (12). Dependabot, a `go mod tidy` check in CI and scheduled security scans, with the current CI state unconfirmed (8).

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.

## 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: CI run results on main and maintainer reply times. Issue and pull request counts came from shields.io badge counts on 18 October (our GitHub record), with no issue text, so how many open issues are crashes or regressions is unknown
- unchecked: GitHub release notes. OSV, the GitHub Advisory Database's public mirror, and NVD list no advisory for Crush
- unchecked: Hyper's terms, privacy policy and plan prices, which render by script at hyper.charm.land. Which Hyper plans are zero-data-retention, given the README's claim and the app's statement that some plans may train Hyper's models
- unchecked: the date of the v0.1.0 tag. `firstReleased` is the first npm version, 0.1.1 on 29 July 2025
- Whether `permissions deny` rules and PreToolUse hooks both hold under `crush run`. The source shows deny hides the tool and hooks run before the permission check, but this wasn't exercised
- The scout's sources included proxy.golang.org, whose robots.txt disallows module paths, so it wasn't fetched. The scout named the server command `crush serve` (as the README does). The command in the source is `crush server`

## Weaknesses

- `crush run` approves every permission request automatically, which the README doesn't mention
- No sandbox, only a fixed list of refused shell commands
- A project's `.crushrc` and `$(...)` in `crush.json` run as code when Crush starts
- Usage metrics are on by default and are linked to the Hyper account after a Hyper login
- No JSON output, turn limit or cost limit for `crush run`, and the client-server API is opt-in and has no authentication

## 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.

- Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session
- Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup
- Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land
- Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag
- Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup

## What the review panel asked for

- dated JSON config removal
- breaking-change headings
- JSON output for crush run
- published OpenAPI document
- turn and time limit flags
- documented exit codes
- deny by default headless
- workspace trust step

## 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.