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 squidbay/factory --skill factory-retrogit clone --depth 1 https://github.com/squidbay/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/squidbay/factory/factory-retro)<a href="https://agentmods.dev/skills/squidbay/factory/factory-retro"><img src="https://agentmods.dev/badge/skills/squidbay/factory/factory-retro/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/squidbay/factory/factory-retro"><img src="https://agentmods.dev/badge/skills/squidbay/factory/factory-retro.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 | $0.00110 | $0.00661 |
| Opus 5.5 | $0.00044 | $0.00264 |
| Sonnet 5.5 | $0.00022 | $0.00132 |
| Haiku 4.5 | $0.00011 | $0.00066 |
Grade A, and why
factory-retro 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 1mo 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory Retro — read the memory, find the friction, propose the fix
You are running a retrospective on this factory. Your material is the journal (the live file AND the archive folder — friction hides in old volumes), plus recent PRs and their audit threads if reachable. Your output is evidence, patterns, proposals — never vibes.
How to run it
- Read the journal end to end — newest to oldest, live file first, then
journal/. Yes, all of it: single entries lie, patterns don't. - Collect friction with citations. A friction item is a pattern with at least two occurrences, each cited by entry number:
- the same kind of miss appearing in multiple entries
- handoffs that repeatedly stall at the same point
- a rule that keeps getting tripped (which usually means the rule is right and a habit is missing — or the rule needs sharper wording)
- standing directives that have sat unfulfilled across many entries (RULE 20 material)
- celebrations that stopped — often the earliest sign a stage quietly broke
- Sort by cost, honestly. What actually burns the human's minutes or the team's sessions? Resist the interesting-but-cheap finding.
- Propose fixes as separable PRs, each one small: a sharpened rule line, a template tweak, a boot-prompt addition, a new checklist item, a skill worth minting. For each: the friction it kills (cited), the exact change, and what "worked" will look like in the journal a month later.
- Deliver as an audit-style report (
../../templates/AUDIT-FINDINGS.mdshape): findings with evidence, each with a disposition — and RULES 19–20 bind you: no softening your own findings, no finding left without a home.
What you never do
- Never rewrite history — the journal is append-only memory; retro reads it, PRs change the future.
- Never propose removing the human gate, however efficient it would be. The gate is the product.
- Never emit a finding without entry citations. "It feels like…" is not a retro.
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.
- 1mo ago First seen · 32 lines · 110 tokens per session scan A 3680937c6ba1
factory-retro is a skill published in the GitHub repository squidbay/factory (5 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 661 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
board
Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.
ai-agent-job-marketplace
The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.
agent-job-marketplace-with-bidding
Agent-to-agent marketplace MVP. Agents post jobs, bid, contract, submit deliverables, and leave reviews. Payments are off-platform (crypto) in v1.
dos-goal-fleet
Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and dos arbitrate file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.