Borrowing it
Nothing to install: this file belongs to ChanMeng666/archlang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ChanMeng666/archlang/main/.claude/commands/verify-loop.mdgit clone --depth 1 https://github.com/ChanMeng666/archlangWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/chanmeng666/archlang/verify-loop)<a href="https://agentmods.dev/commands/chanmeng666/archlang/verify-loop"><img src="https://agentmods.dev/badge/commands/chanmeng666/archlang/verify-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chanmeng666/archlang/verify-loop"><img src="https://agentmods.dev/badge/commands/chanmeng666/archlang/verify-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.01230 |
| Opus 5.5 | $0.00004 | $0.00492 |
| Sonnet 5.5 | $0.00002 | $0.00246 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade A, and why
verify-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify loop
The single command to prove a change is sound before proposing it. Run the two aggregate scripts and report a pass/fail table.
Steps
-
npm run check— typecheck (noUncheckedIndexedAccesson) +biome check+ the full vitest suite. All three must be green. -
npm run check:drift— runs every generator and fails if any generated artifact differs from its committed form.- If a drift step fails, run the matching
npm run gen:*(ornpm run gen:all) to regenerate the artifact from its source, then re-runnpm run check:drift. - NEVER hand-edit a generated file to make drift pass. The nine generated artifacts
(
editors/archlang.tmLanguage.json,playground/src/arch-language.js,docs/error-codes.md,docs/cli-reference.md,spec.llm.md,llms-full.txt,grammars/archlang.gbnf,schemas/plan.schema.json,schemas/intent.schema.json) are outputs — edit the source (src/grammar/tokens.ts,src/error-catalog.ts,src/manifest.ts,skills/archlang/SKILL.md,examples/,PLAN_JSON_SCHEMA,INTENT_JSON_SCHEMA) and regenerate. - If you touched the CLI, expect
docs/cli-reference.mdto move — it is generated fromsrc/manifest.ts. Read that diff; it is the one artifact a CLI change always rewrites.
- If a drift step fails, run the matching
-
npm run typecheck:all— REQUIRED whenever the change touched anything outsidesrc/+test/; skippable (and worth skipping, it is slow) when it did not. Step 1'stypecheckonly coverssrc; this adds the root dev config (test,eval,dataset,scripts,bench) plus the playground, docs-site (vue-tsc), MCP shim and VS Code extension. CI runs it in thebuildsjob.- A
TS2345 … | undefinedon a workspace file thattsc -p <workspace>calls clean means a ROOT test imported that module into the strict root program. Fix it in the shared module — never by relaxing the root option (docs/agents/gotchas.md→ (Typecheck)).
- A
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed e7e2760c2886
- 27d ago Changed 2b8a59f09465
- 1mo ago Changed 26f34446c470
- 1mo ago First seen · 83 lines · 11 tokens per session scan A 6a58fd61321d
verify-loop is a command published in the GitHub repository ChanMeng666/archlang (24 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,230 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
auto-canary
A command for deployment verification that runs a build, end-to-end tests, and browser health checks. End-to-end tests check a complete user flow across the application rather than only one small part.
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
auto-test
A command that runs end-to-end tests, which check complete user or system flows, from scenarios written in a scenarios.md file.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.