AutoHotkey

# Fix list: AutoHotkey

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/autohotkey, the October 2026 research run, assessed 14 October 2026. Grade D, 52.8 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 AutoHotkey: 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, 24 out of 100, up to 13.3 more on the total

Why it scored 24: No credential model. Scripts run with every right of the user who starts them, the closest case to one all-powerful key (10 of 30). No read-only mode, permission scoping or confirmation step for actions (3 of 20). Scripts read window text, controls and the clipboard, which can carry untrusted content, and no guidance on prompt injection was found (3 of 15). `ListLines`, `KeyHistory` and the debugger show what a script did, with no audit log (4 of 15). No SECURITY.md, no published advisories and no security.txt could be read. A code signing policy is linked from the home page and could not be read past the bot check (4 of 20).

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. Agent ergonomics, 46 out of 100, up to 8.8 more on the total

Why it scored 46: The command line adds no tool definitions to context, but output is whatever the script writes, with no structured format (15 of 25). Output size and filtering are up to the script. Window functions take title, class, process and exclusion criteria (8 of 20). `/ErrorStdOut` puts load-time errors on stderr and `/Validate` exits non-zero on a load error, while runtime errors open a dialog unless the script uses `OnError` or `try` (12 of 20). Keystrokes and clicks cannot be safely retried and there is no dry run beyond `/Validate` (4 of 20). One executable, scripts on standard input with `*`, and an experimental DLL host. No SDK in a second language (7 of 15).

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.

## 3. Reliability, 61 out of 100, up to 7.8 more on the total

Why it scored 61: Read with the local-software lines, since the owner runs the interpreter. Official builds are a zip and a setup executable on GitHub releases for 32-bit and 64-bit Windows. The supported Windows versions were on autohotkey.com, which a bot check blocked, so not confirmed (18 of 20). The repository has no CI workflow and no test suite (0 of 25). GitHub Issues was disabled from 2017 until October 2026 and now shows one open issue and ten open pull requests, the oldest from 2022. Bug reports go to the forum, which we could not read (15 of 25). A dated changelog for every release. 2.0.x releases carry fixes only and additions go to 2.1 alphas, though the changelog records regressions such as one `broken by v2.0.20` and fixed in 2.0.30 (13 of 15). Version 2.0 is the stable line (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.

## 4. Schema & documentation, 54 out of 100, up to 7.5 more on the total

Why it scored 54: Graded as a scripting language driven from the command line. No machine-readable contract for the language or the command line (0 of 25). No llms.txt found, and the documentation is HTML in the AutoHotkeyDocs repository (0 of 10). 356 function reference pages state what each function does, its parameters and when it raises an error (17 of 20). Parameters are documented with types, defaults and allowed values, in a dynamically typed language (9 of 15). Every function page has examples, and errors raised are named per function, with the `Error` class hierarchy documented (13 of 15). Versioned releases and a dated changelog back to 2003 (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.

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

Why it scored 60: Read with the self-hosted rule. Free software with nothing to buy, so 20 + 20 + 20. No x402, MPP or L402 (0 of 40).

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

Why it scored 72: 2.0.30 on 9 October 2026 (30). 2.0.27 to 2.0.30 between 28 August and 9 October 2026, plus 2.1 alphas 31 to 35 (20). The changelog credits merged pull requests from outside contributors, but pull requests from 2022 to 2025 remain open with no decision, and the forum where bugs are reported could not be read (12 of 25). No MCP server or package registry entry. Release assets are current on GitHub (7 of 15). No CI and no dependency tooling in the repository (3 of 10).

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. Transparency & trust, 73 out of 100, up to 2.4 more on the total

Made of editorial 73, provenance 73.

Why it scored 73: The editorial half. GPL-2.0 on the repository and on the home page (30). No privacy statement for the software. A search of the interpreter source found no network code, and the docs describe the one optional update check (15 of 30). The README says v1 is not maintained, and deprecated switches such as `/iLib` are marked in the docs, with no dated deprecation policy (10 of 20). The update check is off by default and documented with its registry switch, and no telemetry was found (18 of 20). The provenance half is computed from the provenance block.

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: could not be fetched (0 of 10)

## 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: www.autohotkey.com robots.txt, security.txt, code signing policy and download pages, which returned a Cloudflare challenge or 403 after one read of the home page on 14 October 2026
- unchecked: bug reports and their response times on the community forum, which sits on the same blocked domain
- unchecked: the supported Windows versions as stated on the download page
- Community MCP servers named ahk-mcp exist. None is from the AutoHotkey project, and none was graded

## Weaknesses

- Windows only, and scripts act with every right of the user who runs them
- No CI workflow or test suite in the repository
- No security policy, security.txt or published advisory was found
- Bug reports go to a forum, and GitHub Issues was only switched on in October 2026
- Runtime errors open a dialog unless the script handles them with `OnError` or `try`

## 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.

- Write output with `FileAppend text, "*"` and pipe the interpreter's output, since stdout does not appear at the console it was launched from
- Run `AutoHotkey64.exe /ErrorStdOut /Validate script.ahk` before running a new script
- Add `OnError` or `try` blocks so a runtime error does not leave a dialog open in an unattended run
- Target v2 syntax. v1 is unmaintained and its scripts do not run on v2

## 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.