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/startgit clone --depth 1 https://github.com/jeet129/praxisWhat 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 | $0.00020 | $0.00433 |
| Opus 5 | $0.00010 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
start 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 3d 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
Bootstrap a new project at this repo.
Step 1 — Run delivery-planner. Capture the project charter at .project/semantic/project-charter.md covering:
- mode (G = greenfield / B = brownfield)
- has_data_plane (true if non-trivial data workloads)
- has_ml (true if ML model training/serving)
- has_agentic_ai (true if LLM/agent features)
- compliance_regimes (list or "none")
- scale_target_qps + availability_target
- is_multi_tenant
- preferred stack(s) + cloud
Step 2 — Establish the architecture-documentation skeleton per architecture-documentation:
.project/working/architecture/overview.md(with TODO placeholders).project/decision/INDEX.md
Step 3 — Read governance/governance.yaml and tell me which gates apply per the charter flags. Distinguish always-on vs conditional.
Step 4 — Ensure the per-project governance overrides exist at .project/governance/model-routing.yaml and .project/governance/autonomy.yaml (the SessionStart hook seeds them from the plugin defaults; copy them yourself if missing). Then ask me ONE concise question set: keep the default adaptive routing and autonomy, or tune for this engagement — (a) force_tier (null | deep — e.g. compliance-critical work), (b) cost_weights (match our model pricing), (c) drive autonomy stop_after (task | slice | phase | gate) and run_budget. Apply my answers to the PROJECT copies only — never edit the plugin's own governance files.
Step 5 — Confirm the Praxis is loaded: 17 agents, 91 SKILLs, 9 workflows.
Then route automatically per using-praxis intent routing: proceed into /discover for greenfield or /audit for brownfield, announcing the transition — pause only if the mode is ambiguous or I object.
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.
- 3d ago First seen · 28 lines · 20 tokens per session scan A 983971f729e4
start is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 433 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.