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 ur-grue/autopunk-media-skills --skill project-retrospectivegit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/project-retrospective)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/project-retrospective"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/project-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/ur-grue/autopunk-media-skills/project-retrospective"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/project-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 47 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.09316 |
| Opus 5 | $0.00018 | $0.04658 |
| Sonnet 5 | $0.00007 | $0.01863 |
| Haiku 4.5 | $0.00004 | $0.00932 |
Grade A, and why
project-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 12d 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Retrospective
What This Skill Does
Takes raw notes about a finished media project and generates a structured LESSONS.md that captures reusable editorial decisions, workflow fixes, timeline findings, and specific carry-over items for the next project.
When To Use This Skill
- After a series, season, or multi-episode project wraps and you want to capture what the team learned before everyone moves on to the next thing
- When a project ran over budget, over schedule, or below quality expectations and you need a written record of why, without blame, before the post-mortem meeting
- Before starting a new project that resembles one you finished recently — run the retrospective on the old project first, then use the LESSONS.md as a planning input
- When a freelancer or contributor is leaving the team and their working knowledge needs to be captured before they go
- At the end of a pilot or proof-of-concept phase, to decide whether the format is worth continuing and what must change if it does
What You Need To Provide
Required:
- Project name and format (podcast series, documentary, article series, YouTube channel launch, newsletter run, etc.)
- What the original brief or goal was — in one or two sentences
- What was actually delivered — scope, episode count, word count, whatever the countable output was
- What went well — even rough bullet points are fine
- What went badly or took too long — same level of detail
Optional:
- Timeline: planned vs. actual dates for key milestones (commission, first draft, rough cut, delivery)
- Team structure: who did what, and whether roles shifted during the project
- Budget notes: where you overspent, where you underspent, what you wish you had costed differently
- Stakeholder or client feedback: quotes, notes from review rounds, approval friction
- Technical or tooling notes: software, equipment, workflows that helped or caused problems
- Audience reception: ratings, downloads, reader feedback, social response — anything that tells you whether the output landed
- Anything that surprised you, positively or negatively
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.
- 12d ago First seen · 401 lines · 37 tokens per session scan A dbc82081be8e
project-retrospective is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 9,316 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 2026-08-30.
Other skills, from other repositories
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
absolute-spec
Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to…
compression
Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number (200 for a cold email, 500 for an op-ed, 6 for a product summary). redundancy catches the specific failure where a phrase says what the verb or context already implied — "going forward" after a…
dealing-with-reporters
Drafts and reviews answers to reporter questions, on-the-record statements, crisis-comms responses, and press-inquiry replies. Implements Andrew Ross Sorkin's 11 rules (taught with Kramon at Stanford GSB) plus AP attribution definitions for off-the-record / background / deep background conversations. Use when a…
warm-intro-finder
Finds the human bridges between the writer and a target — mutual contacts, alumni networks, ex-colleagues, podcast connections, board overlaps — and ranks them by how likely they are to make a useful introduction. Different from connection-finder (which finds "like you" content hooks). This one finds people who can…