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 skills/harnessprotocol/harness-kit/pr-sweepnpx skills add harnessprotocol/harness-kit --skill pr-sweepgit clone --depth 1 https://github.com/harnessprotocol/harness-kitWhat 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 | $0.00115 | $0.01795 |
| Opus 5 | $0.00057 | $0.00898 |
| Sonnet 5 | $0.00023 | $0.00359 |
| Haiku 4.5 | $0.00012 | $0.00179 |
Grade A, and why
pr-sweep 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Sweep
A cross-repo PR sweep: discover → enrich → triage → review → act → report.
Announce at start: "I'm using the pr-sweep skill to sweep all open PRs."
Step 1: Discover All Open PRs
gh search prs \
--author @me \
--state open \
--json number,title,url,isDraft,repository,headRefName,baseRefName,reviewDecision \
--limit 100
Parse the result into a working list. Skip drafts immediately — they're not ready for action.
If you have more than 20 non-draft PRs, report the count and ask the user if they want to proceed or filter by repo.
Step 2: Enrich Each PR
For each non-draft PR, fetch CI and merge state in parallel (dispatch subagents or batch calls):
# CI status
gh pr checks <number> --repo <owner/repo> --json name,state,conclusion
# Merge state (up-to-date, behind, conflicting, etc.)
gh pr view <number> --repo <owner/repo> --json mergeStateStatus,mergeable
Build a status object per PR:
{
repo, number, title, url,
ciStatus: passing | failing | pending | none,
mergeState: clean | behind | dirty | blocked,
reviewDecision: APPROVED | CHANGES_REQUESTED | REVIEW_REQUIRED | null
}
Step 3: Triage
Classify each PR into one category (in priority order — first match wins):
| Category | Condition |
|---|---|
MERGE_READY |
CI passing, review approved or not required, merge state clean |
PENDING_CI |
CI still running, everything else clean |
NEEDS_REVIEW |
No reviews yet (reviewDecision null or REVIEW_REQUIRED) |
BEHIND_BASE |
Merge state is behind |
CI_FAILING |
CI has failed conclusions |
CHANGES_REQUESTED |
Reviewer has requested changes |
CONFLICTING |
Merge state is dirty (merge conflicts) |
BLOCKED |
Anything else preventing merge |
Show the triage table to the user and wait for confirmation before taking any action:
PR Triage
─────────────────────────────────────────────────────────────
MERGE_READY owner/repo #42 feat: add caching layer
NEEDS_REVIEW owner/repo #38 fix: auth token refresh
BEHIND_BASE other/repo #11 refactor: split service
CI_FAILING other/repo #9 feat: new export format
CHANGES_REQUESTED repo #7 fix: race condition
─────────────────────────────────────────────────────────────
Plan: merge 1, review 1, rebase 1, attempt CI fix 1, flag 1.
Proceed?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 215 lines · 0 tokens per session scan A a5df49b5995b
pr-sweep is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,795 once invoked, about $0.0006 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 skills, from other repositories
git-commit
Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.
occupancy-calculator
Calculate code occupant loads by area with gross/net factors and jurisdiction checks. Use for "how many people can this space hold," IBC Table 1004.5, egress inputs, or occupancy-load reports; not for workplace headcount planning.
zoning-analysis-nyc
Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.
csv-to-sif
Export a project's FF&E product-library CSV as dealer-system SIF. Use to produce a .sif schedule; use sif-to-csv for the reverse direction.
epd-parser
Extract GWP, life-cycle stages, certifications, and impact metrics from an EPD PDF. Use when given a declaration to parse; not to find or compare EPDs.
product-data-cleanup
Clean a local FF&E CSV schedule by normalizing casing, dimensions, units, language, materials, and formatting. Use when asked to clean, fix, or standardize product data.