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/auditgit 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/audit)<a href="https://agentmods.dev/commands/jeet129/praxis/audit"><img src="https://agentmods.dev/badge/commands/jeet129/praxis/audit.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 | $0.00015 | $0.00642 |
| Opus 5 | $0.00008 | $0.00321 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
audit 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.
What it actually says
Brownfield engagement first-week sequence. Run in order:
Day 0 — Setup. Initialize the .project/ memory tree if absent (semantic / decision / episodic / operational / procedural / working / telemetry). Seed the per-project governance overrides: copy the plugin's governance/model-routing.yaml and governance/autonomy.yaml to .project/governance/ if not present. Then ask me ONE concise question set: keep default adaptive routing and autonomy, or tune for this engagement — force_tier, cost_weights, drive stop_after + run_budget. Apply answers to the PROJECT copies only. (Brownfield default worth suggesting: stop_after: slice until characterization-test coverage is trusted.)
Day 1 — codebase-comprehension SKILL.
Activate Tech Writer (narrate) + Lead Developer (structure). Produce .repo-intel/ outputs:
- System map (Level 1 + 2 of C4 derived from actual deployed system, not aspirational diagrams).
- Data flows (sync + async; cross-boundary).
- Build + deploy story (what runs where; how it gets there).
- Runtime model (what processes / containers / functions live).
- Hot paths (highest-traffic surfaces).
Save to
.project/semantic/codebase-overview.mdplus per-service notes.
Day 2 — architecture-documentation reconciliation.
Compare deployed reality vs any existing C4 diagrams + ADRs. Surface discrepancies. Per item, decide:
- Fix the docs (default).
- OR open a
tech-debt-managemententry if docs reflect intended target. Update.project/working/architecture/overview.md.
Day 3 — tech-debt-management brownfield audit.
Interview me about what feels hard. Run static analysis (complexity / duplication / coverage) with output captured to .project/working/static-analysis.log — consume the top-N summary per dimension (worst 20 files by complexity, duplication clusters, coverage gaps), never the full tool dump. Produce triaged register at .project/operational/debt-register.md. Limit to 20-50 items. Classify each per Fowler's quadrants (prudent/reckless x intentional/inadvertent). Prioritize by payoff x risk x cost.
Day 4 — impact-analysis for the proposed enhancement.
All four lenses (Static + Runtime + Contract + Historical). Surface the blast radius. Recommend: proceed / proceed-with-conditions / scope-blocker. Save to .project/operational/impact-analyses/.
Day 5+ — Phase A starts via /discover.
Common rationalizations to ignore:
- "I'll skim the code; I don't need comprehension." -> brownfield without comprehension ships incidents. Always run.
- "200-item register is fine." -> no. Triage to 20-50. The register is a queue, not a graveyard.
- "Static analysis is the same as impact-analysis." -> no. Four lenses. The IDE doesn't see contracts or history.
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 · 36 lines · 15 tokens per session scan A 5f0cf17205a0
audit is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 642 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
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.