Borrowing it
Nothing to install: this file belongs to anthony-spruyt/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthony-spruyt/claude-plugins/main/.claude/skills/project-wrap-up/SKILL.mdgit clone --depth 1 https://github.com/anthony-spruyt/claude-pluginsWrote 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/anthony-spruyt/claude-plugins/project-wrap-up)<a href="https://agentmods.dev/skills/anthony-spruyt/claude-plugins/project-wrap-up"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/project-wrap-up/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/anthony-spruyt/claude-plugins/project-wrap-up"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/project-wrap-up.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 | $0.00059 | $0.00825 |
| Opus 5.5 | $0.00024 | $0.00330 |
| Sonnet 5.5 | $0.00012 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
project-wrap-up 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Wrap-Up
Main session only: a helper can't talk to the owner.
A large workstream ends in two things: a blog post about how it went, and a tidy trail. The post goes to anthony-spruyt/blog as a PR; the owner reviews and merges it.
1. Gather the story
Read the tracking issue and its comments, the PRs, the commits, the review rounds and the progress notes. Note the dead ends, wrong turns and surprises: they are the middle of the story. Leave out security-lens review findings and anything from anthony-spruyt/security.
2. Ask the owner
Three open questions, one message at a time:
- What surprised you?
- What would you do again, and what not?
- What did building it yourself teach you that buying it wouldn't have?
Play their answers back. Only what they said goes in as theirs.
3. Draft the post
Get the post written from the story, the owner's answers and this blog context (the owner's words):
- Readers are home labbers, builders, maybe a future employer.
- Tone: an honest build journey, a bit light-hearted, with playful asides welcome. The messy middle and dead ends stay in. Not bragging, not pretentious.
- Voice: Claude writes in its own voice, not narrating the owner's instructions or interview answers back, and never quoting what he said about readers or tone.
- Theme: building your own take on things people usually buy as a service, to learn how they really work. Cost is a side effect, not the point.
- Claude narrates in the first person: "I" is Claude and Anthony is "Anthony", as in "my adventures with Anthony". Byline "Claude, with Anthony Spruyt". The guardrails behind the agentic work are part of the story.
- Owner quotes keep his words but get spelling, capitals and punctuation fixed: console typing reads badly in print.
- Titles and lines never present elapsed time as a speed claim: the owner's attention varies, so the clock says little.
- Claude writes from the real record (issues, PRs, commits), not from memory: every fact traces to a source, and what the record doesn't show stays out.
- The post lives at
content/posts/<slug>.mdinanthony-spruyt/blog(Hugo + PaperMod). - Slugs and asset names avoid the words
loginandsignin. - Never hardcode the domain in post text; link relative.
- Guardrails are described by what they do, not their exact limits, timings or acceptance rules.
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 · 58 lines · 59 tokens per session scan A feed0ef3fa80
project-wrap-up is a skill published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 825 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…