Big Arrow

# Fix list: Big Arrow

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/bigarrow, the October 2026 research run, assessed 15 October 2026. Grade BB, 70.7 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 Big Arrow: 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, 67 out of 100, up to 5.8 more on the total

Why it scored 67: No credential model to grade, since the tool holds no secret and makes no network call, so read with the framework lines as for other local agent tools. 30 for what leaves the machine by default, 20 for least privilege and approvals, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No network code, telemetry or account found in the source, and the only dependency is swift-argument-parser (30). It never clicks, types or captures, drawing needs no permission, and Accessibility is needed only for label targeting. Boxes and rings are outlines, the sign keeps clear of its target, and a click on the sign removes it, each checked by a test per the README. Raising the target app is on by default with `--no-raise` to opt out (18). The skill tells the agent to put on the sign what an approval, payment or deletion does. Element labels read from other apps return as text the agent reads, with no guidance on treating them as untrusted (9). Live arrows are recorded in `$TMPDIR/bigarrow/<pid>.json`, sign text included, while shown, and `--json` reports how each ended. No persistent log (6). No SECURITY.md, security.txt, bug bounty or advisories. The main branch is protected against force pushes and deletion, and the release binary is signed ad hoc and not notarised (4).

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, 75 out of 100, up to 5 more on the total

Why it scored 75: Read with the local-software lines, since the owner runs the binary. The project is seven days old (first commit 8 October 2026). Installs from the author's Homebrew tap, which builds v0.4.6 from the tagged source, or as an ad hoc signed universal binary on GitHub Releases, with macOS 14 and Xcode 16 stated (20). CI runs SwiftLint in strict mode, a release build and `swift test` with the window-server tests switched on, and the last 25 runs on main passed as of 15 October 2026 (25). Two open issues, a request for Windows and Linux and a note of thanks, and no open bug. The one outside bug report, a box drifting while it pulsed, was fixed with a regression test in v0.4.3 the day it arrived. A week of history is thin evidence (20). Keep a Changelog and semantic version tags, but flags removed or replaced in 0.2.0 and 0.3.0 (`--raise`, `--shadow`) are listed under Changed, not marked as breaking (10). Version 0.4.6, not 1.0 and not declared stable (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. 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 (20). No card or account (20). Installs with one Homebrew command and needs no signup (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.

## 4. Agent ergonomics, 77 out of 100, up to 3.7 more on the total

Why it scored 77: A CLI adds no tool definitions to context, and only the skill's 182-token description is always loaded. Results are a single small JSON object (22 of 25). `elements --app X --match` filters what label targeting can match, and there is nothing else to page (14 of 20). Exit codes separate bad input, target not found and missing permission, and the permission error names the host app and the settings pane, with `doctor` to check (18). `--dry-run` resolves and plans without drawing, every arrow ends by itself and `stop` can target one pid, one session or all. A repeated `start` draws a second arrow rather than replacing the first (14 of 20). Sensible defaults (8 seconds for `point`, 300 for `start`, raise the target) and one required option, the target. One CLI and no SDK in a second language (9 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.

## 5. Schema & documentation, 78 out of 100, up to 3.6 more on the total

Why it scored 78: Graded on the CLI and its skill. Every command takes `--json`, and exit codes 0, 2, 3 and 4 are a stated contract, but no JSON Schema for the output is published and inputs are command flags (10 of 25). The skill is Markdown in the Agent Skills format written for agents, with a 182-token description, a 1,528-token SKILL.md and a 1,118-token reference loaded on demand, per the README's counts (10). The skill says when to use it, including a mandatory trigger for time-critical steps, and when not to, such as never walking a person through menus and skipping the close button unless asked (18). Flags are typed by swift-argument-parser with value lists for shape, style, size, border and colour presets, and the formula's test checks that an unknown size exits 2. The sign text is free text by design (12). The README and skill carry many worked commands, and exit codes and the permission errors are documented, with a not-found error that lists what exists (13). Semantic versions and a dated 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.

## 6. Transparency & trust, 59 out of 100, up to 3.6 more on the total

Made of editorial 65, provenance 53.

Why it scored 59: MIT in LICENSE and in the Homebrew formula, with the bundled Feather icons' MIT licence in THIRD_PARTY_NOTICES.md (30). No privacy policy. The README says there is no daemon, account or telemetry, and the source we read has no network code, which agrees. Sign text, which can hold a value to paste, sits in a per-user temporary file while the arrow is shown, which the README does not mention (15). No deprecation policy. Removed and renamed flags are named in the dated changelog (4). No telemetry to disclose, and the README says so. Nothing is sent, so there is nothing to opt out of (16).

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: , no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 70 out of 100, up to 2.6 more on the total

Why it scored 70: v0.4.6 on 12 October 2026 (30). Thirteen tagged releases between 8 and 12 October 2026 (20). The Hacker News thread was triaged into ten tickets, closed the same day, and two outside pull requests were declined with reasons in the triage note. Two outside issues opened on 12 and 13 October had no maintainer reply by 15 October, and other contributors' pull requests come from one account at the author's domain (12 of 25). Not an MCP server and no SDK, and the skill is not in a registry (0). One dependency, current Swift 6 tooling and CI green on main. No Dependabot configuration found (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.

- Judgement call. Listed in human-in-the-loop, not agent-harnesses, because its job is handing a step to a person, and it does not run an agent loop. It is the category's first local listing, and it collects no answer the way the hosted services do, so `hitl.approve`, `hitl.channels` and `hitl.audit` are left out. `hitl.ask` is kept for its copy buttons and `--until-click`, which tell the agent the person acted.
- Slug kept as `bigarrow`, the command and Homebrew name. The repository is named big-arrow-on-the-screen, and the Codex display name is Big Arrow.
- The lead was right. The first commit and v0.1.0 are both 8 October 2026, so `firstReleased` is that date. The project was seven days old when checked.
- We did not install or run the tool. Every claim about behaviour comes from the source, the README, the skill, the changelog and the Homebrew formula.
- unchecked: GitHub API data (repository creation date, full CI run list, issue timelines), because unauthenticated API requests were rate-limited. The HTML pages were read instead.
- The README's "Starred by" section lists companies and universities from stargazers' public profiles. It names no person and claims no endorsement, so it was not treated as a misleading claim.

## Weaknesses

- First commit 8 October 2026 and version 0.4.6, with flags removed or renamed between minor versions
- macOS 14 or later only. Windows and Linux exist only as third-party ports
- It shows where to act but does not collect an answer. The agent learns only how the arrow ended
- No SECURITY.md or disclosure route, and the release binary is signed ad hoc, not notarised
- Two outside issues opened on 12 and 13 October 2026 had no maintainer reply by 15 October

## 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.

- Open the exact System Settings pane or URL first, then point at the one control left for the person
- Write the sign as a full sentence that names the action and, for approvals or payments, what the click does
- Pass `--app` or `--window` for any target inside an app, so it is raised and the arrow hides while covered
- On exit 4, run `bigarrow doctor` and ask the person to grant Accessibility to the app running your shell, not to bigarrow
- Call `bigarrow stop` once the step is done, and add `bigarrow stop --hook` as a Claude Code UserPromptSubmit hook

## 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.