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/justhamade/triadjs/testgit clone --depth 1 https://github.com/justhamade/triadjsWhat 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 | $0.00032 | $0.00689 |
| Opus 5 | $0.00016 | $0.00345 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the triad-cli skill for command reference and the triad-behaviors skill for assertion failure diagnosis.
Run the Triad test suite for the current project and report results. If $ARGUMENTS is non-empty, pass it through as the filter: triad test --filter $ARGUMENTS.
Steps
-
Run
triad test(ortriad test --filter $ARGUMENTSif arguments were provided). Capture both stdout and the exit code. -
If every scenario passed, print a one-line summary and stop.
-
If scenarios failed, diagnose each failure using the categories below. Do NOT just re-print the runner output — translate it into an actionable fix.
Failure categories and fixes
Unrecognized assertion: "..."
The then phrase doesn't match any built-in pattern. Rewrite it using a phrase from the triad-behaviors skill phrase table. Common mistakes:
- Single quotes → use double quotes
"expect X to be Y"→ use"response body has X \"Y\"""status is 201"→ use"response status is 201"nullvalue → let the response schema enforce nullability instead
Handler returned status N which is not declared in this endpoint's responses
The handler returned ctx.respond[N](...) or a raw { status: N, body } for a status not in responses. Either add N to responses or fix the handler to return a declared status.
Response body for status N does not match declared schema: <path>: <message>
The handler's output doesn't satisfy the response schema. Usually one of:
- Repository returned fields the DTO doesn't declare →
.pick(...)to narrow - Response DTO is missing a field the repository produces → add it to the model
- A
.nullable()/.optional()mismatch → align the schema with what the handler actually returns
Behavior's request <part> does not satisfy the endpoint's declared schema
The scenario's .body()/.params()/.query()/.headers() is missing a required field or has the wrong type. Fix the scenario's setup to match the schema, or fix the schema if the requirement is wrong.
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 · 53 lines · 32 tokens per session scan A c95838ab244c
test is a command published in the GitHub repository justhamade/triadjs (23 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 689 once invoked, about $0.0002 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.