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 skills add broomva/harness-engineering --skill harness-engineering-playbookgit clone --depth 1 https://github.com/broomva/harness-engineeringWrote 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/skills/broomva/harness-engineering/harness-engineering-playbook)<a href="https://agentmods.dev/skills/broomva/harness-engineering/harness-engineering-playbook"><img src="https://agentmods.dev/badge/skills/broomva/harness-engineering/harness-engineering-playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/broomva/harness-engineering/harness-engineering-playbook"><img src="https://agentmods.dev/badge/skills/broomva/harness-engineering/harness-engineering-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
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 | $0.00081 | $0.01187 |
| Opus 5.5 | $0.00032 | $0.00475 |
| Sonnet 5.5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
harness-engineering-playbook 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- harness-engineering-playbook — 89% identical, 19 lines differ
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering Playbook
Use this skill to operationalize the practices from OpenAI's Harness Engineering guide in a repo that agents can run against repeatedly and safely.
What To Load
- Use
references/openai-harness-practices.mdfor the full practice-to-artifact mapping. - Use
references/rollout-checklist.mdfor phased adoption in active repos. - Use
references/wizard-cli.mdfor Typer wizard command flows. - Use
assets/templates/when creating or updating harness files.
Inputs
- Target repository path.
- Existing command surface (
make,npm,cargo,pytest, etc.). - Existing CI workflows and branch protections.
Workflow
- Baseline the repo and detect existing workflows.
- Bootstrap harness artifacts and templates.
- Apply all nine Harness Engineering practices.
- Run harness audit checks and repair gaps.
- Iterate after real agent runs.
Step 1: Baseline The Repo
- Identify language/toolchain and canonical entrypoints.
- Inventory existing checks, scripts, and CI jobs.
- Record current pain points for agent runs: setup drift, unclear docs, flaky tests, missing trace IDs, slow loops.
Use a short baseline note inside PLANS.md so decisions remain durable.
Step 2: Bootstrap Harness Artifacts
Preferred entrypoint:
python3 scripts/harness_wizard.py init <repo-path> --profile control
Profiles:
baseline: only core harness artifacts.control: baseline + control-system primitives.full: control + entropy controls (nightly audit + entropy checks).
Direct shell fallback:
Run:
./scripts/bootstrap_harness.sh <repo-path>
This script installs safe defaults from assets/templates/:
AGENTS.mdPLANS.mddocs/ARCHITECTURE.mddocs/OBSERVABILITY.mdMakefile.harness(+-include Makefile.harnessinMakefile)scripts/audit_harness.shscripts/harness/{smoke,test,lint,typecheck}.sh.github/workflows/harness.yml
By default, existing files are not overwritten. Pass --force to replace template-managed files.
What ships with it
29 files 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.
- agents/openai.yaml 281 B
- assets/templates/.github/workflows/harness.yml 434 B
- assets/templates/.github/workflows/nightly-harness-audit.yml 417 B
- assets/templates/AGENTS.md 1.8 KB
- assets/templates/docs/ARCHITECTURE.md 1.1 KB
- assets/templates/docs/control/ACTUATORS.md 643 B
- assets/templates/docs/control/CONTROL_SYSTEM.md 444 B
- assets/templates/docs/control/CONTROLLER.md 508 B
- assets/templates/docs/control/ENTROPY.md 561 B
- assets/templates/docs/control/FEEDBACK_LOOP.md 437 B
- assets/templates/docs/control/SENSORS.md 685 B
- assets/templates/docs/control/SETPOINTS.md 392 B
- assets/templates/docs/control/STABILITY.md 697 B
- assets/templates/docs/OBSERVABILITY.md 894 B
- assets/templates/evals/control-loop-metrics.yaml 584 B
- assets/templates/Makefile.harness 240 B
- assets/templates/PLANS.md 811 B
- assets/templates/scripts/audit_harness.sh 2.3 KB runs code
- assets/templates/scripts/harness/entropy_check.sh 1.2 KB runs code
- assets/templates/scripts/harness/lint.sh 973 B runs code
- assets/templates/scripts/harness/smoke.sh 1.0 KB runs code
- assets/templates/scripts/harness/test.sh 843 B runs code
- assets/templates/scripts/harness/typecheck.sh 1.1 KB runs code
- references/openai-harness-practices.md 2.8 KB
- references/rollout-checklist.md 1.6 KB
- references/wizard-cli.md 1.6 KB
- scripts/audit_harness.sh 2.3 KB runs code
- scripts/bootstrap_harness.sh 2.7 KB runs code
- scripts/harness_wizard.py 7.1 KB runs code
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.
- 2mo ago First seen · 157 lines · 81 tokens per session scan A 66b53db02096
harness-engineering-playbook is a skill published in the GitHub repository broomva/harness-engineering (26 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,187 once invoked, about $0.0003 per session on Opus 5.5. 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.
harness-engineering-playbook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-engineering-playbookbroomva/harness-engineering | Skill | 26 | 4mo ago | MIT | A | 81 | Codex |
| autoanybroomva/autoany | Skill | 3 | 6mo ago | MIT | A | 207 | Claude Code, Codex |
| symphonybroomva/symphony | Skill | 11 | 4mo ago | Apache-2.0 | C | 147 | Claude Code, Codex |
| index-refreshpaperclipai/paperclip | Skill | 113k | today | MIT | A | 43 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 113k | today | MIT | A | 30 | Claude Code, Codex |
| hive.chart-creation-foundationsaden-hive/hive | Skill | 11k | 5d ago | Apache-2.0 | A | 133 | Claude Code, Codex |
| openai-whisper-apispinabot/brigade | Skill | 11k | 3d ago | MIT | A | 20 | Claude Code, Codex |