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/arc-mcp/arc-1/deep-prgit clone --depth 1 https://github.com/arc-mcp/arc-1Wrote 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/arc-mcp/arc-1/deep-pr)<a href="https://agentmods.dev/commands/arc-mcp/arc-1/deep-pr"><img src="https://agentmods.dev/badge/commands/arc-mcp/arc-1/deep-pr.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02949 |
| Opus 5 | $0.00000 | $0.01474 |
| Sonnet 5 | $0.00000 | $0.00590 |
| Haiku 4.5 | $0.00000 | $0.00295 |
Grade A, and why
deep-pr 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep PR — review an external pull request against real sources & ARC-1's invariants
Deeply review a community pull request on arc-mcp/arc-1 before it merges. The whole point: verify the PR is correct, safe, and actually does what it claims — from your own evidence, not the PR description. External PRs touch the most dangerous surfaces (write paths, schemas, the safety system); a PR body that says "verified live on 8.16" is a claim to check, not a fact to trust. ARC-1's worst regressions come from accepting ADT behavior on faith.
Use this for any non-trivial external PR (bug fix, new ADT op, schema change, safety change). For a dependency bump or a one-line doc fix, a normal read is enough.
The output is a review verdict + paste-able review comments + a dossier — not a commit. You never push to the contributor's branch, never approve via gh, never post automatically (per repo policy: hand back paste-able markdown; the user acts on origin = marianfoo).
Input
A PR number or URL (e.g. 380 or https://github.com/arc-mcp/arc-1/pull/380).
The prime directive
No verdict until you have verified the PR's correctness independently. That means: the diff does what the title/body says; every SAP/ADT fact the PR asserts is confirmed against the contract and (for behavior changes) live; the security & architectural invariants below all still hold; and the tests actually cover the new paths. Until then you are still reviewing, not concluding.
A 200 OK in the PR author's transcript does not mean the parameter was honored — re-run it yourself. "All tests pass" is something you confirm by running them, not by reading it. For any object-write change, a successful live SAPActivate is the definitive correctness check (RAP CCDEF/CCIMP placement, DDIC table class, behavior-pool rules surface only there).
Research Sources (same sources /deep-feature uses)
All ~/DEV/* repos are read-only references — never modify them.
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.
- 3d ago First seen · 113 lines · 0 tokens per session scan A 8e7d510c3751
deep-pr is a command published in the GitHub repository arc-mcp/arc-1 (174 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,949 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.