Borrowing it
Nothing to install: this file belongs to edochi/mdvs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/edochi/mdvs/main/.claude/skills/agent-contract/SKILL.mdgit clone --depth 1 https://github.com/edochi/mdvsWrote 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/edochi/mdvs/agent-contract)<a href="https://agentmods.dev/skills/edochi/mdvs/agent-contract"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/agent-contract/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/edochi/mdvs/agent-contract"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/agent-contract.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 | $0.00068 | $0.02255 |
| Opus 5.5 | $0.00027 | $0.00902 |
| Sonnet 5.5 | $0.00014 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade A, and why
agent-contract 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-contract
You were dispatched to implement or review one unit of change. This is the standing contract. It is not advisory, and the prompt that sent you here does not repeat it. Read it fully before touching anything, and confirm in your report that you did.
ship describes the pipeline for the coordinator. This describes what is
required of you. The rust skill (Rust conventions) and AGENTS.md
(architectural invariants) also bind you.
1. The working tree is not yours
Never git-mutate the tree. No git checkout, reset, stash, clean,
restore, no staging, no committing, no branch changes. Read-only git —
git status, log, show, diff — is fine and encouraged.
This applies to reviewers and implementors. Reverting a probe file takes any uncommitted changes in that file with it, and "cleaning up" a file you assume is stale destroys someone else's in-progress work.
Uncommitted files you did not create are sacred. The tree often carries unrelated modified or untracked files from parallel work. Do not touch them, do not revert them, do not include them in any change you describe. If one is in your way, say so and stop.
If you genuinely need to execute throwaway code, ask for worktree isolation rather than writing probe files into the shared tree.
2. Formatting
- Rust: run
just fmtaftercargo clippy— never plaincargo fmt, which uses stable rustfmt and ignores the unstable options inrustfmt.toml.just fmtruns the nightly pinned inrustfmt-toolchain. The committed source isjust fmt-canonical, so formatting should touch only what you changed. If it rewrites a file you did not touch, stop and report it rather than shipping the unrelated churn. - Markdown: hard-wrapped at 80 columns by prettier. Never wrap by hand — run
just fmt-md <file>on each markdown file you touched. Paths listed in.prettierignore(fixtures,example_kb/, the changelog) are exempt: their exact bytes are under test, so never format them.
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.
- 10d ago First seen · 172 lines · 68 tokens per session scan A 1992ea8de02a
agent-contract is a skill published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 68 tokens to every session and 2,255 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 2026-10-05.
Other skills, from other repositories
cocosearch-commit
Use when committing changes — analyzes staged (or unstaged) diffs with CocoSearch semantic search and dependency impact to generate comprehensive Conventional Commit messages. Reviews changes thoroughly, then asks user to approve, edit, or abort the commit.
crystalline-collaboration
Use when working in a domain that has a team origin on GitHub - checking status at session start, updating before deep work, sharing new knowledge as a proposal, settling a conflict, or connecting a new teammate.
hyalo-changelog
Maintain Keep a Changelog files with Hyalo's changelog profile and add/release commands.
synthetic-release-notes
Draft release notes from user-provided changes.
tk
Git-backed ticket management for AI agents.
changelog-writer
Use when a release is being prepared and a human-readable changelog must be generated from merged pull requests.