Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/chrstian6/contractornpx agentmods add commands/chrstian6/contractor/auto-approveWrote 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/chrstian6/contractor/auto-approve)<a href="https://agentmods.dev/commands/chrstian6/contractor/auto-approve"><img src="https://agentmods.dev/badge/commands/chrstian6/contractor/auto-approve.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 5.1 | $0.00017 | $0.00323 |
| Opus 5 | $0.00009 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
auto-approve 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 8d 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.
What it actually says
Run the toggle with the argument the user gave (default to status when they
gave none):
python3 .claude/scripts/auto-approve.py ${ARGUMENTS:-status}
Then report the result in one or two lines:
status— say which mode is wired and stop.on— full auto-approval: every tool call is approved without a prompt unless apermissions.denyrule or a guard hook (dangerous commands, orchestrator-only git, protected files, build artifacts, secret scan) objects. This is the unattended-loop mode. Tell the user the session must be restarted (or/cleared) for the hook change to take effect, and thatCLAUDE_AUTO_APPROVE=0in the environment disables it without editing anything.readonly— the narrow mode: only provably read-only calls skip the prompt; everything that writes still asks.off— back to normal permission prompts.
Do not edit .claude/settings.json by hand to do this — the script is the
supported path, and the settings file is write-protected for agents.
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.
- 8d ago First seen · 30 lines · 17 tokens per session scan A 1076ba481d89
auto-approve is a command published in the GitHub repository chrstian6/contractor (40 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 323 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 2026-08-30.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.