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 yfge/agent-harness-skills --skill repo-contracts-and-boundariesgit clone --depth 1 https://github.com/yfge/agent-harness-skillsWrote 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/yfge/agent-harness-skills/repo-contracts-and-boundaries)<a href="https://agentmods.dev/skills/yfge/agent-harness-skills/repo-contracts-and-boundaries"><img src="https://agentmods.dev/badge/skills/yfge/agent-harness-skills/repo-contracts-and-boundaries/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/yfge/agent-harness-skills/repo-contracts-and-boundaries"><img src="https://agentmods.dev/badge/skills/yfge/agent-harness-skills/repo-contracts-and-boundaries.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00933 |
| Opus 5 | $0.00020 | $0.00466 |
| Sonnet 5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
repo-contracts-and-boundaries 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Contracts And Boundaries
Overview
Convert architectural and structural-quality intent into checks that prevent new drift instead of relying on repeated prose warnings.
This skill owns both repository contracts and quality gardening because both use the same mechanism: collectible rules, diff gates, audit reports, baselines, and gradual debt reduction. For shared harness terms, see ../../references/harness-patterns.md; when contract files are absent, use references/build-when-missing.md; for schema, fixture, and golden-payload contracts, see references/schema-fixture-contracts.md; for metrics and generated snapshots, see references/quality-policy.md.
When To Use
- The user asks to define, protect, audit, or encode architecture boundaries, directory ownership, choke points, allowlists, baselines, or contracts.
- The repository has layering rules, but agents still add bypass calls or wrong dependencies.
- The user asks for structural metrics, quality reports, debt thresholds, regression budgets, or a gradual cleanup loop.
- You need to distinguish diff checks from full audit checks.
Inputs Needed
- Architecture docs or expected layering.
- Current directory structure and known historical debt.
- Rules to protect: dependency direction, file size, public entrypoints, data access, interface boundaries, or similar constraints.
- Existing quality reports, generated snapshots, and CI or scheduled-run policy.
Execution Order
- First: Read architecture docs, current code, existing checks, reports, and baselines to identify real boundaries and debt.
- Then: Design mechanical rules, collectible metrics, diff checks, audit reports, baselines, and allowlists.
- Finally: Output executable contracts, generated evidence, and a gradual convergence strategy.
Step-by-Step Process
- Search for
ARCHITECTURE.md, contract docs, lint scripts, baseline files, and allowlists. - List protected rules; each rule must be checkable by script or review.
- If architecture or contract surfaces are missing, bootstrap the minimum files and checker shape from
references/build-when-missing.md. - Separate new drift from historical debt: new drift should fail, historical debt should enter a baseline.
- Add only metrics tied to a concrete structural risk; keep them automatically collectible and avoid aggregate quality scores.
- Design
--mode difffor changed files and--mode auditfor full-repository reports. - For each violation, output path, rule or metric, current value, threshold, reason, and suggested direction.
- Define when baselines or allowlists may change, who owns generated snapshots, and what repayment note is required.
What ships with it
3 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.
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.
- 12d ago First seen · 107 lines · 41 tokens per session scan A 8bd3fbe51533
repo-contracts-and-boundaries is a skill published in the GitHub repository yfge/agent-harness-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 933 once invoked, about $0.0002 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
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
reviewing-code-quality
Reviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict. Use when a change risks oversized files, needless layers, feature logic leaking into shared code, or clever indirection. Do not use for a trivial obvious edit, or for a check that is only about whether…
review-deep
Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.
review-orchestrator
Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.
audit
Use for PACEflow internal full audit: run five independent review agents, verify evidence from code/tests/logs, de-duplicate findings, and produce a severity-ranked report for release gates or comprehensive code review.