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 OneDro1d/dark-factory --skill scope-retiregit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/scope-retire)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/scope-retire"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/scope-retire/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/onedro1d/dark-factory/scope-retire"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/scope-retire.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 | $0.00144 | $0.01091 |
| Opus 5 | $0.00072 | $0.00545 |
| Sonnet 5 | $0.00029 | $0.00218 |
| Haiku 4.5 | $0.00014 | $0.00109 |
Grade A, and why
scope-retire 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scope-retire — archive a notepad, keep the history
Retiring a notepad means "stop treating this as an active objective" — not "delete it".
The journal (sessions/*.jsonl), the handoffs, the memory-index (wing=<prefix>) entries,
and the git remote all stay. Retirement is a reversible status change plus a clean final
snapshot. See ../../DESIGN.md (§6 file contracts, §16 acceptance).
Never destructive. This skill does not rm journals, does not empty the memory index,
does not delete the GitHub repo, and does not force-push over history. If the operator wants
hard deletion, that is a separate manual action they perform themselves — surface it, don't
do it.
Procedure
1. Confirm the notepad and its state
- Resolve the notepad directory (cwd or the operator-named scope). Confirm it is a notepad (has SCOPE.md + repos.manifest.json + sessions/).
- Read SCOPE.md done-criteria and report which are met vs open, so the operator retires with eyes open. Retiring with open criteria is allowed (abandonment) — just say so.
2. Write a final snapshot into NOTES.md
Do one last rewrite of NOTES.md (§6.1): set Current goal to a one-line outcome
("Retired : <done | abandoned because …>"), Next action to "none — scope retired",
and leave the Key refs / Blockers as the honest final state. This is the summary a future
reader lands on first; keep it terse and un-redacted of caveats.
3. Append a retirement milestone to the journal (do NOT rewrite history)
Append one new event to the current session journal
(sessions/<ISO8601>_<id>.jsonl) — never edit or delete existing lines:
{"ts":"<now>","kind":"milestone","text":"scope retired: <outcome>","refs":[],"commit":null,"session":"<id>"}
The append-only journal is the history of record; retirement adds a closing entry, it does not erase what came before.
4. Mark SCOPE.md retired
Add a status line at the top of SCOPE.md, e.g.
> **Status:** RETIRED <date> — <one-line outcome>. This is the durable, human-visible
flag that the notepad is shelved. Leave Objective + Done-criteria in place for the record.
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.
- 9d ago First seen · 86 lines · 144 tokens per session scan A 6cb083e55af4
scope-retire is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 144 tokens to every session and 1,091 once invoked, about $0.0007 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 2026-09-01.
Other skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.