Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/chanmeng666/archlang/verify-loopgit clone --depth 1 https://github.com/ChanMeng666/archlangWhat 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 | $0.00011 | $0.01224 |
| Opus 5 | $0.00005 | $0.00612 |
| Sonnet 5 | $0.00002 | $0.00245 |
| Haiku 4.5 | $0.00001 | $0.00122 |
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 2d 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,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 (AGENTS.md → Gotchas;docs/testing.md§4).
- A
-
Conditional gates — run the ones the diff earns:
- touched
docs/*.mdordocs-site/⇒npm run docs:build(the core suite never compiles the site). - touched
playground/⇒npm run build && npm run playground:build:only && npm run e2e:playground. - touched
docs-site/⇒npm run build && npm run docs:build:only && npm run e2e:docs. - touched
packages/mcp⇒npm run mcp:build && node packages/mcp/scripts/check-dist-resources.mjs. - touched
editors/vscode⇒npm run vscode:build:only && npx vitest run editors/vscode(the stdio + bundle-freshness tests SKIP without a built bundle).
- touched
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.
- 2d ago First seen · 83 lines · 11 tokens per session scan A 6a58fd61321d
verify-loop is a command published in the GitHub repository ChanMeng666/archlang (8 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 1,224 once invoked, about $0.0001 per session on Opus 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
README
Git workflow and quality assurance commands for the claude-skills repository.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
execute
Interactive workflow for workspace isolation, pane-delegated implementation, testing, review, and cleanup.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.