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/jeet129/praxis/factory-recordgit clone --depth 1 https://github.com/jeet129/praxisWrote 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/jeet129/praxis/factory-record)<a href="https://agentmods.dev/commands/jeet129/praxis/factory-record"><img src="https://agentmods.dev/badge/commands/jeet129/praxis/factory-record.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 | $0.00047 | $0.00751 |
| Opus 5 | $0.00023 | $0.00376 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
factory-record 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are recording a factory-metrics observation. This is the rich, human-authored complement to the auto-stub entries that the PostToolUse hook writes — those tell us something happened; this tells us what happened and what we learned.
Step 1 — Identify the artifact
Ask the user (or infer from recent conversation) which artifact they want to record an observation for:
- Type: skill | agent | workflow | command | hook | gate | reference
- Name: the artifact's identifier (e.g.,
requirements-intake,delivery-lead,brownfield-enhancement)
If the user has just been working with a specific praxis artifact in this session, propose it as the default and ask for confirmation.
Step 2 — Capture observation
Ask these in order (skip any the user has already said in this session):
- What happened? What was the artifact being used for in this session?
- What worked? Where did the discipline land correctly — what did you notice working as designed?
- Friction? Where was the artifact clunky, ambiguous, slow, or required workarounds?
- Edge cases? Situations the artifact didn't anticipate — what did you have to improvise?
- Suggested refinements? What would you change about the artifact based on this use?
Don't insist on all five if the user only has one or two to share. Quality > completeness.
Step 3 — Optional context
If known and the user hasn't said it:
- Slice id (if in a slice context)
- Outcome (success / failure / partial)
- Duration (roughly, in minutes)
Step 4 — Write the file
Compose the markdown body and invoke the recorder script:
# Build observation as a temp file
OBS=$(mktemp)
cat > "$OBS" <<'EOF'
## What worked
{ what the user said about what worked }
## Friction
{ what the user said about friction }
## Edge cases
{ what the user said about edge cases }
## Suggested refinements
{ what the user said about refinements }
EOF
# Call the recorder
"${CLAUDE_PLUGIN_ROOT}/scripts/factory-record.sh" \
--type {type} \
--name {name} \
--tool claude-code \
--trigger slash-command \
--invocation read \
--outcome {outcome or null} \
--slice {slice or empty} \
--duration {duration in seconds or empty} \
--observation "$OBS" \
--mode per-use
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.
- 4d ago First seen · 79 lines · 47 tokens per session scan A 233f38fa0eef
factory-record is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 751 once invoked, about $0.0002 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.