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/testgit 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 | $0.00026 | $0.00528 |
| Opus 5 | $0.00013 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
test 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.
What it actually says
User Input
$ARGUMENTS
Workflow
Step 1: Discover Specs
| Input | Behavior |
|---|---|
| (empty) | Glob for .nlpm-test/*.spec.md in cwd |
| path to a .spec.md file | Test that single spec |
| path to a directory | Glob for *.spec.md in that directory |
If no specs found → "No test specs found. Create specs in .nlpm-test/ directory. See skills/nlpm/testing/SKILL.md for the spec format."
Display discovered specs:
Found {N} spec(s):
.nlpm-test/my-agent.spec.md → agents/my-agent.md
.nlpm-test/core-skill.spec.md → skills/core/SKILL.md
Step 2: Load Config
Read .claude/nlpm.local.md if exists. Extract score_threshold (default: 70). This is used as the fallback min_score when specs don't specify one.
Step 3: Run Tests
For each spec, dispatch the nlpm:tester agent with:
- The spec file content
- The artifact file content (if it exists)
- The scoring rubric reference
Batch specs in groups of up to 3 (each spec requires reading 2 files + analysis).
Step 4: Report
NLPM Test Report
Spec Artifact Result Checks
─────────────────────────────────────────────────────────────────────────────────
{for each spec}
Overall: {passed} passed, {failed} failed, {red} red
{if any RED:}
RED (write these artifacts next):
{artifact_path} — spec exists but artifact doesn't
{if any FAIL:}
FAIL (fix these):
1. {artifact_path} — {specific failure description}
{if all PASS:}
All specs pass. GREEN.
Error Handling
- Spec has no
artifact:frontmatter → "Spec missingartifact:field: {spec_path}" - Spec references invalid type → "Unknown artifact type '{type}' in {spec_path}. Valid: agent, skill, command, rule, hook, prompt"
- Malformed YAML frontmatter in spec → "Malformed spec: {spec_path}"
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 · 74 lines · 26 tokens per session scan A 5caa28fbd377
test is a command published in the GitHub repository xiaolai/nlpm (133 stars, last pushed 2d ago), licensed ISC. It adds 26 tokens to every session and 528 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.