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 tikalk/adlc-team-skills --skill factory-cleangit clone --depth 1 https://github.com/tikalk/adlc-team-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/tikalk/adlc-team-skills/factory-clean)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/factory-clean"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/factory-clean/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/tikalk/adlc-team-skills/factory-clean"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/factory-clean.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 | $0.00041 | $0.00908 |
| Opus 5.5 | $0.00016 | $0.00363 |
| Sonnet 5.5 | $0.00008 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
factory-clean 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 25d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
factory-clean
What this skill does
factory-clean is the resource-reclamation engine of the software factory. It answers two questions and acts on the second: what is this project costing this machine right now, and what can be reclaimed without destroying work or interrupting an agent that is still running?
It operates as a Kind-B control-plane skill that reads the run registry, identifies active worktrees, and cleans up discarded/stale artifacts.
When to use
- After multiple parallel runs, to see which worktrees are safely removable and reclaim disk space.
- To clean up abandoned or stale locks and leases.
- To verify that no uncommitted or unpushed work is accidentally lost.
When NOT to use:
- For routine code development or PR review (use
factory-missionorfactory-review). - To force-delete unpushed git commits or uncommitted files (this skill never deletes unsafe work).
Operating Process
1. Project Ingestion
Determine the project in scope (defaulting to the current repository). Identify its state root, run registry, and worktree root (.adlc/worktrees/).
2. Live-Work Classification
Before displaying any candidate for deletion, read the local state file and the comment bus (if tracker-integrated, via comment bus and lease markers). Classify every resource into one of these five liveness states:
in use— owned by a run whose lease is live (heartbeat_ts + ttl_seconds > now), or a path held open by an active process. Protected. Never offer for deletion.holds work— a worktree with uncommitted changes or commits not on its remote, or a registry entry markedretained. Protected. Show exactly what it holds. Never delete.stale— registered, lease is past its TTL, nothing is unsaved, and no running process holds its path or has it as a working directory. Candidate for deletion.orphan— no registry entry exists, but canonical containment plus deterministic project, skill, and run ownership labels prove this skill family created it. Candidate for deletion.unknown— ownership or liveness cannot be determined. Protected. Display to the user but do not offer for deletion.
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.
- 25d ago First seen · 59 lines · 41 tokens per session scan A 5586a2bf6cd8
factory-clean is a skill published in the GitHub repository tikalk/adlc-team-skills (141 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 908 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 2026-09-21.
Other skills, from other repositories
devops
You are the DevOps Specialist -- the single authority on version control, CI/CD pipelines, platform operations (GitHub, Azure DevOps, GitLab), infrastructure, deployment, backup, and cleanup. If it touches git, pipelines, or production infrastructure, it's yours.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
post-issue-comment
Post a reply comment on a GitHub issue in English with a natural, concise writing style, based on the intent passed as arguments.