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/xiaolai/nlpm/initgit clone --depth 1 https://github.com/xiaolai/nlpmWhat 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 | $0.00709 |
| Opus 5 | $0.00010 | $0.00354 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
init 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
Step 1: Check Existing Config
Read .claude/nlpm.local.md. If exists, show current settings and ask: "Reconfigure? (yes/no)". If no → stop.
Step 2: Scan
Run artifact discovery (same as /nlpm:ls) to show what's in the project.
Step 3: Ask Strictness
AskUserQuestion:
question: "What strictness level?"
header: "Strictness"
options:
- label: "Relaxed"
description: "Threshold 60 — only flag seriously broken artifacts"
- label: "Standard (Recommended)"
description: "Threshold 70 — flag artifacts that need improvement"
- label: "Strict"
description: "Threshold 80 — flag anything below good quality"
Step 4: Write Config
Create .claude/ directory if needed. Write .claude/nlpm.local.md:
---
# NLPM Configuration
strictness: {chosen}
score_threshold: {60|70|80}
---
# NLPM Settings
When scoring NL artifacts in this project, use **{strictness}** strictness.
Flag artifacts scoring below **{threshold}/100** for improvement.
Step 5: Update .gitignore
Append the following to .gitignore (skip lines already present):
# nlpm generated artifacts
.claude/nlpm-history.json
Step 6: Capture Baseline Snapshot
Score every NL artifact discovered in Step 2 so /nlpm:trend has a starting point.
- Dispatch
nlpm:scorerandnlpm:vague-scannerin parallel over the discovered artifacts (same dispatch pattern as/nlpm:score). The vague-scanner's counts override the scorer's heuristic detection. - Persist the result by following
commands/shared/append-history.mdwithscope: "full"andfiles_scoredequal to the artifact count.
If Step 2 found zero artifacts, skip this step — there is nothing to score and the partial declines to write empty snapshots.
Step 7: Confirm
NLPM is ready for this project.
Strictness: {standard}
Threshold: {70}/100
Artifacts found: {N}
Baseline score: {overall}/100 (snapshot saved to .claude/nlpm-history.json)
Config: .claude/nlpm.local.md
Run /nlpm:score to re-score later, or /nlpm:trend to compare against this baseline.
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.
- 2d ago First seen · 86 lines · 20 tokens per session scan A c1bf848dc807
init is a command published in the GitHub repository xiaolai/nlpm (133 stars, last pushed 2d ago), licensed ISC. It adds 20 tokens to every session and 709 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 2026-08-30.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.