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 agentmods add commands/watt-mind/factory/factory-frictiongit clone --depth 1 https://github.com/watt-mind/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/commands/watt-mind/factory/factory-friction)<a href="https://agentmods.dev/commands/watt-mind/factory/factory-friction"><img src="https://agentmods.dev/badge/commands/watt-mind/factory/factory-friction.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.01064 |
| Opus 5 | $0.00007 | $0.00532 |
| Sonnet 5 | $0.00003 | $0.00213 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
factory-friction 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 5d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture harness friction from an interactive session where no orchestrator transcript exists.
Runs dispatched through runners/run-agent.sh or orchestrator/tick.mjs already write JSONL to ~/.factory/logs/ — /factory-retro measures those mechanically via factory friction. This command is the backstop when you ran /factory-work, /factory-merge, /factory-ticket, /factory-ship, or similar directly in a harness (Claude, Codex, Pi, Cursor) without FACTORY_RUN_ID set.
1. When to use
- At the end of an interactive factory command session (also invoked inline from those commands' closing step).
- Ad hoc when a session was painful and you want it recorded before context is lost.
- Skip when
FACTORY_RUN_IDis set — the transcript is the primary sensor; don't duplicate it with memory.
2. What qualifies
Same bar as docs/friction-log.md — only two things:
Repeats or likely repeats. A tool error you hit twice, a retry loop (same command 3+ times), the same floor violation recovered from more than once in the session (sleep waits, unquoted zsh globs, wrong Linear label names, missing FACTORY_ROOT).
Per-ticket costs that could be paid once. The same expensive setup on every ticket in a batch, a harness gap that blocked every subagent (slash command not installed, MCP missing, worktree script absent).
Do not file: one-off ticket bugs (those go to product Triage via /factory-capture), product intent questions, vague annoyances with no actionable harness layer, or anything that is already that ticket's problem rather than the harness's.
3. Scan the session
$ARGUMENTS names specific friction if given; otherwise scan the conversation for qualifying items. If more than one distinct friction surfaced, file each separately — don't merge unrelated shapes into one issue.
4. Search before filing
Search Linear (factory ticket or docs/protocol.md §13) for:
- Existing
FIP:issues describing the same shape - Prior issues whose body contains
## Session frictionwith the same Shape - Entries in
docs/friction-log.md(F-*) already tracking it
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.
- 5d ago First seen · 80 lines · 14 tokens per session scan A 952b6573aad2
factory-friction is a command published in the GitHub repository watt-mind/factory (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 1,064 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
release
Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.
check
Run the full local quality gate — TypeScript check, build, dependency audit (prod-only), skill registry validate. Fast pre-commit / pre-suggestdeploy sweep.
app-init
Start a new mobile app project — runs requirements intake, then CEO vision, then PRD + architecture in parallel.
app-status
Show the current state of the project — vision, sprint goal, board, blockers, daily report.
app-recover
Recover an interrupted run — reconcile the ledger, the board, the worktrees and the wave, then restart from a known state.
app-context
Create a deterministic provenance manifest before an agent starts work.