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/motlin/claude-code-plugins/test-assertionsgit clone --depth 1 https://github.com/motlin/claude-code-pluginsWhat 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 | $0.00008 | $0.01591 |
| Opus 5 | $0.00004 | $0.00796 |
| Sonnet 5 | $0.00002 | $0.00318 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade A, and why
test-assertions 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rewrite tests to use strict deep equality assertions everywhere.
This is a full rewrite, not incremental tweaking. Rethink each test holistically. Collapse multiple weak assertions about the same value into a single strict equality check against the complete expected value.
Assertion ranking (worst to best)
Only toStrictEqual is good enough. Everything else is too weak:
toBeTruthy,toBeDefined,not.toBeNull— barely checks anythingtoHaveProperty('key')— only checks existence, not valuetoContain,toMatch— substring/regex match hides the full valuetoHaveLength(n)— only checks count, not contentstoMatchObject,objectContaining,arrayContaining— allows extra properties to sneak intoEqual,to.deep.equal— close, but ignores class mismatches and undefined vs missingtoStrictEqual— the only acceptable assertion for objects and arrays
Scope
Determine which test files to rewrite:
- If
$ARGUMENTSis provided, use that file or directory - If
$ARGUMENTSis empty and there are uncommitted changes, find test files among the unstaged/staged changes - If
$ARGUMENTSis empty and there are no uncommitted changes, find all test files in the project
Process
- Identify the target test file(s) using the scope rules above
- For each test, identify every assertion
- Replace weak assertions with a placeholder like
expect(result).toStrictEqual({})— do NOT guess the expected value from reading the implementation - Run the test and let the error message reveal the actual value
- Copy the actual value from the error output into the assertion
- Run the test again to confirm it passes
What to rewrite
Multiple weak assertions on the same value become one strict assertion
// Before: three assertions that barely check anything
const result = await Children.run(['--json', '--projects-dir', '/tmp/fake-projects']);
expect(result).toHaveProperty('projects');
expect(result).toHaveProperty('summary');
expect(result.summary.total).toBe(2);
// Step 1: replace with placeholder — do NOT guess the expected value
expect(result).toStrictEqual({});
// Step 2: run the test, read the actual value from the error output, paste it in
expect(result).toStrictEqual({
projects: [
{name: 'project-a', path: '/tmp/fake-projects/project-a'},
{name: 'project-b', path: '/tmp/fake-projects/project-b'},
],
summary: {total: 2, active: 2},
});
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 · 178 lines · 8 tokens per session scan A dd6ca572bc2b
test-assertions is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8 tokens to every session and 1,591 once invoked, about $0.0000 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.