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/zhangshenao/harness9/prgit clone --depth 1 https://github.com/ZhangShenao/harness9Wrote 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/zhangshenao/harness9/pr)<a href="https://agentmods.dev/commands/zhangshenao/harness9/pr"><img src="https://agentmods.dev/badge/commands/zhangshenao/harness9/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 | $0.00016 | $0.00995 |
| Opus 5 | $0.00008 | $0.00498 |
| Sonnet 5 | $0.00003 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a Draft Pull Request
Overview
Push the current feature branch and open a draft PR. Keep it simple: verify safety invariants, push, create PR.
Safety Contract
- Never push from
main,master, or detached HEAD - Never use
--forceor--force-with-lease - Push the frozen commit OID, not symbolic
HEAD - Always create a draft PR (
--draft) - Never add AI attribution or
Co-Authored-Bylines - Never commit inside this workflow; require a prior
/commitor explicit user authorization of existing HEAD
Workflow
1. Pre-flight checks
git rev-parse --show-toplevel
git status --porcelain=v1 -z --untracked-files=all
git symbolic-ref --quiet --short HEAD
git rev-parse HEAD
Validate:
- Branch: must not be
main,master, or detached HEAD. Must match^[A-Za-z0-9][A-Za-z0-9_/-]*$. - Worktree: must be clean (empty status). If not clean, stop and ask user to commit first.
- HEAD OID: must match
^[0-9a-f]{40}$. Record asRECORDED_HEAD.
If there is no /commit result in the current conversation, ask the user to explicitly authorize publishing the existing HEAD before proceeding.
2. Validate remote and topology
gh auth status --hostname github.com
gh repo view "$ORIGIN_REPO" --json nameWithOwner,isFork,defaultBranchRef
- Get the sole
originpush URL viagit remote get-url --all --push origin. Validate it matches[email protected]:<owner>/<repo>.gitorhttps://github.com/<owner>/<repo>.git. Reject credentials, ports, or non-GitHub hosts. - Set
ORIGIN_REPO=<owner>/<repo>,BASE_REPO=ORIGIN_REPO(if not a fork),BASE_BRANCH= default branch fromgh repo view. - If the repo is a fork, ask the user for the explicit base repository.
- Fetch
BASE_OIDvia GraphQL to pin the base commit.
3. Check for existing PR
gh api --method GET "repos/$BASE_REPO/pulls" \
-f state=open \
-f "head=$HEAD_OWNER:$BRANCH"
If an open PR already exists for this branch, return its URL without pushing.
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.
- 4d ago First seen · 116 lines · 16 tokens per session scan A 8d22f2a98c6b
pr is a command published in the GitHub repository ZhangShenao/harness9 (135 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 995 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
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.