Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. 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/adrienm7/ergopti/main/.agents/skills/retire-artifact/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/retire-artifact)<a href="https://agentmods.dev/skills/adrienm7/ergopti/retire-artifact"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/retire-artifact/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/adrienm7/ergopti/retire-artifact"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/retire-artifact.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 | $0.00029 | $0.00785 |
| Opus 5.5 | $0.00012 | $0.00314 |
| Sonnet 5.5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
retire-artifact 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 today.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retiring a document
Stale documents are worse than absent ones: they are read as current. But a document that has outlived its process usually still carries a few live items, and deleting it blind loses them. The whole job is separating the two.
Never trust the document about itself
Status labels rot faster than anything else in a repo. Check every claim against the code, and prefer the code's answer.
Two verified examples from the same file:
- A July plan asserted a timings accessor had "no production consumer". The keystats walker reads it.
- The same plan asserted a set of updater menu keys did not exist, and used that to defer an entire i18n batch. All the keys were present in the shared locales.
An archived audit's "Open" labels are the same class of lie — the fix usually landed, often with a test whose header cites the finding id. Grep for the id before believing the label.
The verdict is per item, not per document
Walk the document item by item and sort each one:
- Delivered — cite the
file:linethat proves it. This is the bulk of an old plan, and it is what makes the deletion safe. - Still open — extract it, with enough context to act without the original: what, where (real paths), why it matters today, and how to verify it. If you cannot write that, you have not understood it well enough to move it.
- Decided against — keep the reason, not the item, and put it under a "do not re-raise" heading. This is the part everyone drops, and it is why the same rejected idea comes back every few months.
- Superseded — a test now guards the invariant. Name the test. The test is the living memory; the prose was the placeholder.
Where extracted work goes
TODO.md at the repo root, curated — a list, not an inventory. Rank by value and
say plainly what each item costs if it stays undone. If everything looks equally
important, nobody will start.
Durable lessons go to the narrow topic under docs/memory/ instead; see the
project-memory skill. The distinction: a lesson stops someone breaking
something, a TODO is work someone will do.
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.
- today Changed 6e5bc4a01c41
- 15d ago First seen · 77 lines · 29 tokens per session scan A a31c5f0cd007
retire-artifact is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 785 once invoked, about $0.0001 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 2026-10-14.
Other skills, from other repositories
pipefy-process-intelligence
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
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.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.