What is project-contract-harness?

A local delivery contract for large or long-running software projects handled by coding agents. It stores plans, tasks, decisions, risks, tests, evidence, and handoff details on disk.

Use it when starting or taking over a complex project, feature, or repository that needs persistent state, project-specific checks, secret-handling rules, and a clear handoff.

It prevents project knowledge and progress from being lost between agent sessions and makes the work easier to check against agreed requirements.

project-contract-harness — Skill for Codex by cyberflax2020

Install

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.

Any agent

npx skills add cyberflax2020/project-contract-harness --skill project-contract-harness-kit

Clone the repo

git clone --depth 1 https://github.com/cyberflax2020/project-contract-harness

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit/github.svg)](https://agentmods.dev/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit)

Your own site

<a href="https://agentmods.dev/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit"><img src="https://agentmods.dev/badge/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit"><img src="https://agentmods.dev/badge/skills/cyberflax2020/project-contract-harness/project-contract-harness-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,598 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00119	$0.02598
Opus 5	$0.00060	$0.01299
Sonnet 5	$0.00024	$0.00520
Haiku 4.5	$0.00012	$0.00260

Measured 11d ago against content hash a4da334b3e2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

project-contract-harness 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 11d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_contract.py, scripts/init_contract.py, scripts/privacy_scan.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

project-contract-harness — 100% identical, 0 lines differ

deploy/claude-project/project-contract-harness-kit/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Contract Harness

Overview

Use this skill to turn a broad engineering objective into a local, enforceable delivery contract. The contract persists the plan, tasks, decisions, risks, secret-access contract, resource guard, evaluation matrix, gaps, evidence, autonomy boundary, and handoff state on disk so a fresh agent can resume without relying on chat history.

This skill is intentionally product-agnostic. Do not copy customer names, private paths, internal service names, credentials, host details, or reference-project specifics into generated artifacts.

First Actions

Identify SKILL_ROOT as the directory containing this SKILL.md.
Identify REPO_ROOT as the target project root. If the user did not specify it, use the current working directory.
Probe for an existing REPO_ROOT/.project-contract-harness/. If it exists, recover from it first: read status, tasks, gaps, gates, evidence, tooling, secret access, artifact index, and handoff before proposing or editing.
Analyze the project before editing, even for a single module or small request: repo shape, existing docs, test framework, package/build commands, runtime constraints, active concurrent work, and user-visible success criteria.
If REPO_ROOT/.project-contract-harness/ does not exist, run:

python3 "$SKILL_ROOT/scripts/init_contract.py" --project-root "$REPO_ROOT"

If the directory exists but lacks current required files, run the initializer without --force to add missing files while preserving existing state.
Convert that analysis into the project harness: update STARTUP.md, CONTRACT.md, PLAN.md, TASKS.md, TOOLING.md, SECRET_ACCESS.md, ARTIFACTS.md, RESOURCE_GUARD.md, EVAL_MATRIX.md, and gates.json before broad code changes.
Read the existing contract files in this order: STARTUP.md, CONTRACT.md, PLAN.md, TASKS.md, STATUS.md, DECISIONS.md, RISKS.md, AUTONOMY.md, TOOLING.md, SECRET_ACCESS.md, ARTIFACTS.md, RESOURCE_GUARD.md, EVAL_MATRIX.md, GAPS.md, EVIDENCE.md, HANDOFF.md.
Check whether another active writer is working in the same repo. If there is a reasonable signal of active concurrent development, stay read-only or restrict edits to explicitly owned files.
Run the contract checker before major edits:

Read the full file on GitHub · 163 lines

Files

What ships with it

17 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.

Changes

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.

11d ago First seen · 163 lines · 119 tokens per session scan A a4da334b3e2f

Subscribe to this mod's changes

project-contract-harness is a skill published in the GitHub repository cyberflax2020/project-contract-harness (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 119 tokens to every session and 2,598 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.

Claude Code Planning Project management agent-skills ai-agents ai-coding automation codex-cli

swarm-plan

Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.

ZaxbyHub/opencode-swarm · 32 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

project-contract-harness