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/stewardgit 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/steward)<a href="https://agentmods.dev/commands/jeet129/praxis/steward"><img src="https://agentmods.dev/badge/commands/jeet129/praxis/steward.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 5.1 | $0.00017 | $0.00504 |
| Opus 5 | $0.00009 | $0.00252 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
steward 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 6d 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.
What it actually says
Quarterly steward cadence. Run as a single 1-2 day block.
Step 1 — Run factory-evaluation against telemetry from the past quarter:
- Skill metrics (per SKILL): invocation rate, trigger precision/recall, time-to-output, output acceptance rate, downstream rework, reference drift, lifecycle state.
- Agent metrics (per role agent): hand-off latency, decision quality (sampled), escalation rate, per-AOP-step time, tool-call efficiency.
- Workflow metrics: completion rate, phase cycle time, Decision Node distribution, gate clearance time, defect leakage, rework rate.
- Governance metrics: evidence-completeness on first submission, time-to-clear, reject + iterate rate.
- Library health: skill count, capability balance, lifecycle distribution, memory volume per type, reference count per skill.
Output: .project/operational/factory-metrics/<quarter>.md.
Step 2 — Activate System Steward agent. Read the factory report end-to-end. Draft the quarterly steward report covering:
- Library health snapshot (skill count in target band; capability balance; lifecycle distribution).
- Findings from factory-evaluation.
- Proposals (lifecycle changes, trigger tunings, reference/pattern additions, consolidations, deprecations).
- For each proposal: evidence + risk + recommendation + rollback plan.
- "Items NOT proposed (deliberately)" section — discipline against over-reacting to noise.
- Cumulative library impact projection.
Step 3 — Route through steward_promotion gate. Evidence pack (per governance.yaml):
- Steward report.
- Factory-evaluation reference.
- Per-proposal evidence + rollback plan.
- Conditional: before/after metrics, eval harness results, candidate change diff, capability balance check.
I review per-proposal; approve or reject with rationale. Rejected proposals become ADRs.
Step 4 — Implement approved changes. Update SKILLs / agents / workflows / governance per approvals.
Common rationalizations to ignore:
- "Nothing changed this quarter; skip." -> telemetry exists; review it. Silence isn't health.
- "We can change skills directly without governance." -> no. Every change routes through steward_promotion. Even small ones.
- "More skills is better." -> no. 70-90 target band. 101+ mandatory consolidation. Knowledge grows in references/patterns/examples.
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.
- 6d ago First seen · 38 lines · 17 tokens per session scan A 1028a54276da
steward is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 504 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.