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 OutlineDriven/odin-claude-plugin --skill issue-intakegit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/issue-intake)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/issue-intake"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/issue-intake.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00824 |
| Opus 5 | $0.00020 | $0.00412 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
issue-intake 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue intake
Contract
| Field | Bound contract |
|---|---|
| Trigger | the user runs /issue-intake with a task idea |
| Authority | Remote: files one GitHub issue; requires explicit human invocation. Preview the filing target and consequence before publication. |
| Side effect | a filed GitHub issue plus a local spec archive and an optional worktree implementer |
| Done | the spec is filed and archived with frontmatter, with any requested implementer spawned |
Inputs
- A task idea, supplied by the user at invocation. Required; if absent, ask before proceeding.
- A target GitHub repository for filing, resolvable from the current
ghcontext or stated by the user. Required before any remote mutation. - An optional request to spawn a worktree implementer bound to the filed issue.
Procedure
- Receive the task idea from the
/issue-intakeinvocation. If none was supplied, ask the user for one and stop until it is provided. Done when: one task idea is in hand. - Interrogate the user to resolve scope: problem statement, acceptance criteria, constraints, and explicit out-of-scope boundaries. Ask targeted questions; stop when the user confirms the spec is complete. Done when: the user confirms the spec covers all four scope dimensions.
- Draft the spec as a GitHub issue title and body from the confirmed scope. The title summarizes the problem in one line; the body states the problem, acceptance criteria, constraints, and out-of-scope boundaries. Done when: the draft issue title and body state these elements.
- Apply redaction gates: scan the draft title and body for secrets, credentials, private identifiers, and any content the user has not approved for public publication. Show the user the redacted title and body and the list of redactions. Proceed only after explicit human approval of the redacted form. Done when: the user approves the redacted draft.
- Preview the filing target (repository and issue title) and the consequence: a public GitHub issue will be created. Require explicit human confirmation before filing. Done when: the user confirms the filing target and consequence.
- File the approved, redacted spec as a GitHub issue in the target repository using the user's authenticated
ghcontext. Done when: a GitHub issue URL is returned. - Archive the spec locally as a markdown file with YAML frontmatter capturing the issue URL, title, and filing timestamp, under the project's spec archive location. Done when: the local archive file exists with frontmatter.
- If the user requested an implementer, spawn a worktree implementer bound to the filed issue. Otherwise stop. Done when: the implementer handle is returned, or no implementer was requested and the skill stops.
What ships with it
1 file 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.
- yesterday First seen · 45 lines · 40 tokens per session scan A d1654c708b24
issue-intake is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 824 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 2026-09-06.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…