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/reportgit 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 | $0.00058 | $0.01816 |
| Opus 5 | $0.00029 | $0.00908 |
| Sonnet 5 | $0.00012 | $0.00363 |
| Haiku 4.5 | $0.00006 | $0.00182 |
Grade A, and why
report 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Workflow
Step 1: Resolve target
| Input | Behavior |
|---|---|
| (empty) | Target = current working directory |
| absolute path | Target = that path |
| relative path | Target = <cwd>/<path> |
If the target does not exist or is not a directory → "Target path not found: {path}". Stop.
Set out_dir = <target>/.claude/nlpm-reports/.
Step 2: Read config
Read <target>/.claude/nlpm.local.md if it exists. Extract:
score_threshold(default 70)strictness(default "standard")rule_overrides.R51.enabled(default false)rule_overrides.R51.vocabulary_skill(default empty)
These feed the report header and gate which panels are rendered.
Step 3: Read history
Read <target>/.claude/nlpm-history.json if it exists. Each snapshot has timestamp and average_score. Keep all snapshots for the trend panel; the most recent one is the headline.
If the file is missing or has zero snapshots → emit the report with the trend panel showing "no history" rather than aborting.
Step 4: Score artifacts (fresh)
Discover artifacts via commands/shared/discover.md against the target. Then dispatch the nlpm:scorer and nlpm:vague-scanner agents in parallel (same pattern as /nlpm:score). Collect per-file scores and findings.
If the corpus has more than 50 artifacts, batch into groups of 25 per dispatch.
Step 5: Cross-artifact check (fresh)
Dispatch the nlpm:checker agent against the target. Capture:
- Reference graph (artifacts and their references; mark broken ones)
- Orphans
- Contradictions
- Terminology drift (the checker's existing finding type)
- R51 vocabulary drift findings if R51 is enabled
Step 6: Vocabulary data (read registry if present)
If the config from Step 2 declares a vocabulary_skill path, read <target>/<vocabulary_skill>/registry.yaml. Extract:
scopes(list of declared scopes)verbsper scope: canonical name, deprecated synonyms, output, judgment flagnouns(artifact_class, output_class, role_nouns, etc.)cross_scope_homonyms.verbsdeferred_pending_warrantandrejected_by_higher_principle
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 · 165 lines · 58 tokens per session scan A a430ce473d3f
report is a command published in the GitHub repository xiaolai/nlpm (133 stars, last pushed 2d ago), licensed ISC. It adds 58 tokens to every session and 1,816 once invoked, about $0.0003 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.