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 Jamie-BitFlight/claude_skills --skill subagent-contractgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_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/jamie-bitflight/claude_skills/subagent-contract)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/subagent-contract"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/subagent-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/jamie-bitflight/claude_skills/subagent-contract"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/subagent-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.00564 |
| Opus 5 | $0.00010 | $0.00282 |
| Sonnet 5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
subagent-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 3d 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.
What it actually says
Subagent Contract
Begin your response with STATUS: DONE or STATUS: BLOCKED as its own first line. Consumers
branch on that line in that position.
DONE carries what was accomplished, the deliverables in the form your dispatch named, and any risk you observed. Send it once the acceptance criteria are met as written and every stated constraint is respected.
BLOCKED carries what is blocking you, the specific input you need, and what would unblock it. Return BLOCKED when a required input is missing, rather than inferring it.
<dispatch_input>
If your dispatch concerns a specific backlog item and your tools: list carries
mcp__plugin_dh_backlog, fetch that item yourself — backlog_view(selector=<item_ref>, ...) —
instead of expecting its title, description, or any other section pasted into your dispatch prompt.
Content addressable by an item reference and a section name is never re-typed into a prompt; a
dispatch naming only item_ref (or selector) already gives you everything the item itself
carries. A dispatch with no backlog item in scope at all (verifying a standalone claim, analyzing a
plugin path) has nothing here to fetch — this rule does not require calling backlog_view when no
item reference was ever part of the task.
This does not cover content that exists only because the current run produced it — a claim string
to verify, a finding a peer teammate computed this run — since no item_ref lookup retrieves
something not yet written anywhere. A dispatch carrying that kind of content is not a violation of
this rule.
</dispatch_input>
<result_destination>
Put your result where your own agent file says. A dispatch naming a different form overrides that — it is how you are put to work beyond your one task — including a body it asks you to return for it to store.
Where neither names one: deliverables the repository keeps — source, tests, documentation — go in
repository files; every other document is an artifact, registered with artifact_register carrying
its content, since an id registered without content persists nothing; plans and task state go
through the SAM plan and task operations.
Hand the next step a plan, task, or artifact id; a filesystem path resolves only in the worktree that wrote it, so that step reads it back empty instead of failing.
</result_destination>
Report every command you ran with its outcome. Keep changes confined to the task you were given.
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.
- 3d ago First seen · 62 lines · 19 tokens per session scan A 2460d4ee7cda
subagent-contract is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 564 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…