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.
git clone --depth 1 https://github.com/harnessworks/harness-starter-kitWrote 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/harnessworks/harness-starter-kit/harness-adopt)<a href="https://agentmods.dev/commands/harnessworks/harness-starter-kit/harness-adopt"><img src="https://agentmods.dev/badge/commands/harnessworks/harness-starter-kit/harness-adopt.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 | $0.00000 | $0.00988 |
| Opus 5 | $0.00000 | $0.00494 |
| Sonnet 5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
harness-adopt 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 7d 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.
/harness adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.
Harness Adopt may modify target repository files, but it must stay conservative: inspect first, preserve the target repository as the source of truth, and add only the smallest useful harness pieces.
Goal
Turn the target repository's real conventions, checks, repeated mistakes, and review expectations into durable harness artifacts: agent instructions, constraints, feedback loops, memory, evaluation, and governance.
This command is for first-time adoption. It is not a blind installer and not a request to copy every starter-kit template.
Procedure
- Treat the current working directory as the target repository root.
- Inspect the target repository before editing:
git status --short --branch- existing
AGENTS.md,CLAUDE.md,.cursor/rules/*, or.github/copilot-instructions.md README.md,CONTRIBUTING.md, package manifests, CI configs, and local verification commands- existing docs under
docs/, especially decisions, failures, conventions, domain notes, and evaluation records
- If
./harness-starter-kitexists, treat it as read-only reference material. If it does not exist and the user asked you to use this kit from GitHub, clonehttps://github.com/harnessworks/harness-starter-kitinto that path for reference. - Read the canonical adoption workflow from the local kit reference when
available:
./harness-starter-kit/docs/adoption-workflow.md./harness-starter-kit/docs/prompts/apply-to-target-repo.md- relevant profile snippets under
./harness-starter-kit/templates/profiles/<profile>/
- Select the smallest useful adoption set for this target. Prefer updating existing docs/configs over adding parallel files.
- Add or update only artifacts that fit the target's existing architecture,
tools, package manager, docs, commands, and conventions. Common candidates:
- agent instructions
- lightweight drift checks
- decision or failure memory templates
- convention or domain notes
- an adoption report with verification and measurement plan
- Do not add CI, pre-commit hooks, dependencies, package scripts, or broad architecture rules unless they match the target's existing workflow and the maintainer asked for that level of enforcement.
- Run relevant local checks using the target repository's existing tools, plus any adopted harness checks.
- Finish with the required report format and state whether the nested
./harness-starter-kitreference should be removed, ignored, or kept before commit.
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.
- 7d ago First seen · 116 lines · 0 tokens per session scan A 9c1ac9e9b197
harness-adopt is a command published in the GitHub repository harnessworks/harness-starter-kit (113 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 988 tokens. 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
coverage
Ingest or inspect test-coverage reports — LCOV, Cobertura/Clover, or coverage.py .coverage (builds the per-test map when contexts are present).
ng-context-pack
Portable command prompt generated from skills/briefing-an-agent/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
ng-red-team
Portable command prompt generated from skills/stress-testing-agent-changes/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
verification-repair
PitWay: Bounded, approve-before-edit correction after every task is done.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.