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/open-prnpx skills add harnessprotocol/harness-kit --skill open-prgit 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 | $0.00111 | $0.01392 |
| Opus 5 | $0.00056 | $0.00696 |
| Sonnet 5 | $0.00022 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
open-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 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open PR
A structured PR preparation workflow: tests → create PR → code review → CI → hand off to merge.
Announce at start: "I'm using the open-pr skill to get this PR ready."
Step 1: Pre-flight — Run Local Tests
Run the test suite before touching anything else. Detect the right command from project files:
| Indicator | Command |
|---|---|
| CLAUDE.md test command | Use that (takes precedence over all below) |
go.mod |
go test ./... |
package.json |
npm test or yarn test |
pyproject.toml / setup.py |
pytest |
Cargo.toml |
cargo test |
If tests fail: Stop. Show the failures clearly. Don't proceed — fix them or ask the user how to handle. Do not skip or bypass test hooks.
If tests pass: Continue.
Step 2: Check for Existing PR
gh pr view --json number,url,state 2>/dev/null
- PR already open: Skip to Step 4 — Code Review.
- No PR: Continue to Step 3.
Step 3: Create the PR
Push the branch
git push -u origin $(git branch --show-current)
Title
Use the most meaningful commit message as a starting point, cleaned up to be concise. Follow conventional commit format (feat:, fix:, refactor:, etc.) if the repo uses it — check recent commits with git log --oneline -10.
Auto-detect labels
Infer labels from the branch name and commits — apply with --label if the label exists in the repo:
| Pattern | Label |
|---|---|
fix/, bug/, "fix" in commits |
bug |
feat/, feature/ |
enhancement |
refactor/, chore/ |
refactor |
docs/ |
documentation |
Skip labels that don't exist in the repo rather than erroring.
PR description template
Fill in every section based on the actual changes — no unfilled placeholders:
## Summary
<!-- What this PR does and why — 2-4 sentences. Lead with intent, not implementation. -->
## Changes
<!-- Key changes. Be specific — not "updated code" but what and why. -->
-
## Test Plan
<!-- How this was verified -->
- [ ] Local tests pass
- [ ] CI checks pass
- [ ] <any manual or integration steps>
## Notes
<!-- Edge cases, follow-ups, known limitations, or anything a reviewer should know -->
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.
- 2d ago First seen · 193 lines · 111 tokens per session scan A 49e589cf7093
open-pr is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,392 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
learn
Guided, hands-on course teaching architects how to use Codex or Claude Code — six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted…
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
epd-to-spec
Write CSI specification language for EPD submittals and sourced GWP limits. Use to add embodied-carbon or EPD requirements to specs; not to parse, find, or compare EPDs.
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.
workplace-programmer
Build office space programs through guided workplace strategy: area splits, room schedules, and planned seat counts. Use to program or size a workplace; not for code occupant-load calculations.