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 engineering-retrospectivegit 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/engineering-retrospective)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/engineering-retrospective"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/engineering-retrospective/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/engineering-retrospective"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/engineering-retrospective.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 | $0.00043 | $0.00958 |
| Opus 5.5 | $0.00017 | $0.00383 |
| Sonnet 5.5 | $0.00009 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
engineering-retrospective 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 1mo 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.
This is a copy
91% identical to engineering-retrospective — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering retrospective
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user requests an engineering retrospective for a named period. |
| Authority | Reversible local: writes only the single report file at reports/engineering-retrospective-<period-slug>.md; rollback is undo. No remote mutation. |
| Side effect | One local write to the authorized report file built from telemetry and review logs. |
| Done | A report file exists at the authorized path containing the period, team breakdowns, evidence-backed habits, and gap accounting. |
Inputs
- Period: the time window named in the request. Required; the retrospective is bounded to it. Resolve it to explicit start and end dates.
- Repository telemetry for the period: commits, pull requests, CI runs. Required; gathered from the local repository.
- Connected tracker telemetry for the period: issues, tickets. Optional; gathered from connected trackers when accessible.
- Review logs for the period: code-review threads, comments, and resolution outcomes. Optional; absent logs are reported as a gap rather than inferred.
Procedure
- Read the period from the request and resolve it to explicit start and end dates. Stop if no period is supplied. Derive the authorized report path as
reports/engineering-retrospective-<period-slug>.mdwhere<period-slug>is the period expressed asYYYYMM-DDor the user's requested slug. Done when: the period is resolved to start and end dates and the report path is named. - Discover the repository and connected trackers. Identify the local repository root by walking up from the working directory to find
.git. Identify connected trackers by inspecting repository configuration and project files: issue trackers linked in.github/,package.jsonmetadata, or project configuration files. Establish source precedence for overlapping telemetry: the local repository is the primary source for commits, PRs, and CI runs; connected trackers are the primary source for issues and tickets; review logs from the repository are primary over tracker-exported review data. When two sources cover the same activity, cite the primary source and note the secondary as corroboration. Done when: the repository root is found, connected trackers are identified or marked absent, and source precedence is established. - Gather telemetry for the period from each discovered source. From the local repository:
git logfor commits in the period,gh pr listor equivalent for pull requests, CI run history for build outcomes. From connected trackers: issues or tickets created or updated in the period. From review logs: review threads, comments, and resolution outcomes. Mark each unavailable source explicitly as a gap with the reason. Done when: every discovered source is gathered for the period or marked as a gap. - Derive team and contributor breakdowns from the gathered evidence. Summarize activity per team or per contributor: commit count, PR count, review participation, issue resolution, and CI pass/fail rate. Attribute each breakdown to the source it was derived from. Done when: breakdowns are derived for every contributor or team with activity in the period.
- Identify habits: recurring patterns, bottlenecks, and practices observed across the period, each tied to the evidence that shows it. Distinguish habits the evidence supports from inferences. Done when: habits are identified with evidence citations.
- Write the assembled retrospective to the authorized report file. Include the period, source coverage and gaps, team breakdowns, habits with evidence, and a one-line summary. Done when: the report file exists at the authorized path with all sections.
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.
- 1mo ago First seen · 43 lines · 43 tokens per session scan A f6cdff7c73b2
engineering-retrospective is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 43 tokens to every session and 958 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to engineering-retrospective, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…