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 product-on-purpose/agent-skills-toolkit --skill askit-build-chain-contractgit clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkitWrote 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/product-on-purpose/agent-skills-toolkit/askit-build-chain-contract)<a href="https://agentmods.dev/skills/product-on-purpose/agent-skills-toolkit/askit-build-chain-contract"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-build-chain-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/product-on-purpose/agent-skills-toolkit/askit-build-chain-contract"><img src="https://agentmods.dev/badge/skills/product-on-purpose/agent-skills-toolkit/askit-build-chain-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 | $0.00061 | $0.00595 |
| Opus 5 | $0.00030 | $0.00298 |
| Sonnet 5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
askit-build-chain-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 11d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
askit-build-chain-contract
Purpose
Author a plugin's chain contract: the explicit declaration of which components may invoke which others (Standard sec 3.6). A chain contract is a CONDITIONAL MUST - required if and only if a component invokes another, so a plugin with no inter-component invocation ships no contract (no empty governance files). Two modes: create authors agents/_chain-permitted.yaml (and the optional agents/_pairing.yaml); improve resolves S4 findings. Authoring depth is in references/authoring-chain-contracts.md. Follows the shared builder contract (../../docs/reference/builder-pattern.md).
When to use
When a skill or subagent declares a chain: to another component and you need to permit it, or when evaluate reports an S4 orphan (an invocation not permitted) or phantom (a contract entry naming a missing component).
create mode
- Scan components for
chain:declarations (which caller invokes which callees). Skip the contract entirely if nothing chains (the conditional MUST). - Author
agents/_chain-permitted.yaml: one entry per caller, listing the components it may invoke. Copytemplates/chain-permitted.yamlif none exists. - Optionally author
agents/_pairing.yamlfor recommended (not required) skill plus subagent pairings. - Evaluate (
node scripts/evaluate.mjs . --json) until S4 is clean: everychain:invocation is permitted (no orphan) and every contract entry names an on-disk component (no phantom).
improve mode
- Run
node scripts/evaluate.mjs . --jsonand read the S4 findings. - For an orphan, add the missing
caller: [callee]permission. For a phantom, fix the misspelled name, remove the stale entry, or create the missing component. - Re-run to confirm S4 is clean.
Scope
The contract is agent-agnostic: one agents/_chain-permitted.yaml (no per-target form). It binds exactly when there is an invocation to make safe (sec 3.6), so it is a safety mechanism, not ceremony. S4 (chain-contract integrity) flags orphans and phantoms; do not ship an empty contract for a plugin that does not chain.
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.
- 11d ago First seen · 31 lines · 61 tokens per session scan A 0dd9bfb1ac2e
askit-build-chain-contract is a skill published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 595 once invoked, about $0.0003 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
modelchk
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…
autobahn
Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
dedash
Remove em-dashes and the dashes standing in for them from a user-owned scope, reading each occurrence in context and choosing the punctuation or wording that fits.
feynman
Press a decision you just made until you can explain it to a skeptic in your own words, or surface the gap where you can't. The Feynman test aimed at a choice: understanding is cheapest to fake the moment after you decide, so a fresh critic presses for what you can't actually explain. Use right after picking an…