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 post-daily-new-issuesgit 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/post-daily-new-issues)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/post-daily-new-issues"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/post-daily-new-issues/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/outlinedriven/odin-claude-plugin/post-daily-new-issues"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/post-daily-new-issues.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 | $0.00041 | $0.01052 |
| Opus 5 | $0.00020 | $0.00526 |
| Sonnet 5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
post-daily-new-issues 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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post daily new issues
Contract
| Field | Bound contract |
|---|---|
| Trigger | A human explicitly requests the daily on-call issue digest; a scheduled invocation may prepare the run but must not use credentials or post without explicit human authorization for that run. |
| Authority | Remote: posts one Slack message in the configured channel; requires explicit human invocation. Preview the bounded issue-tracker query, destination channel, release URL, and posting consequence before using credentials. |
| Side effect | Read only the stated UTC window from the stated issue-tracker scope and, only when it contains issues, create one Slack message in the configured channel containing the total and at most three issue bullets. |
| Done | If the window contains no issues, make no Slack mutation; otherwise, prove that the configured channel received one message containing the release URL, total issue count, and top three issue counts. |
Inputs
Require the UTC window start and end, the name of the issue tracker the digest reads from, its organization and project scope, its read credentials, the destination Slack channel, Slack posting credentials, and the release URL. The end must be later than the start, both bounds must include an explicit UTC offset, and the issue-tracker and Slack credentials must be limited to the stated scopes. An optional human-supplied label may identify the digest; it must not alter the query window or destination. Do not infer a missing bound, scope, channel, credential, or release URL.
Procedure
- Before accessing either service, present the UTC window, the issue tracker's organization and project, Slack channel, release URL, and the consequence that a nonempty result creates one remote Slack message. Obtain explicit human authorization for this exact run; if it is absent, stop without using credentials. Done when: explicit human authorization is obtained for this exact run.
- Validate the time bounds, identifiers, release URL, and credential availability at their input boundaries. Stop on malformed, missing, or broader-than-stated input rather than widening the query or destination. Done when: all inputs are validated at their boundaries.
- Fetch issues created in the inclusive-start, exclusive-end UTC window from only the authorized issue-tracker organization and project. Preserve each issue's count and display identity needed for the digest; do not mutate the issue tracker. Done when: issue-tracker issues are fetched from the authorized scope within the stated window.
- If the fetch returns no issues, stop without calling Slack or emitting digest content. Done when: the empty-window no-op is confirmed or the fetch is nonempty.
- Compute the total number of fetched issues, rank them by count from highest to lowest, and retain no more than the first three for issue bullets. Build one message containing the release URL, the total, and each retained issue's display identity and count. Done when: the message is built with release URL, total, and top-three issue identities and counts.
- Preview the final message and confirm that its channel, URL, total, and issue counts derive from the validated inputs and fetched result. If any value cannot be traced to them, stop without posting. Done when: every message value is traced to validated inputs and the fetched result.
- Post the message once to the configured Slack channel. Treat Slack's successful response identifying the created message and channel as proof; do not post a second copy to obtain proof. Done when: Slack's response identifies the created message and channel.
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.
- 4d ago First seen · 37 lines · 41 tokens per session scan A 94dbed7908a2
post-daily-new-issues is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,052 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…
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…