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/validategit 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 | $0.00033 | $0.00553 |
| Opus 5 | $0.00016 | $0.00277 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the triad-cli skill for command reference, and triad-endpoint or triad-schema depending on what the validator surfaces.
Run triad validate --strict and act on the output.
Steps
-
Run
triad validate --strict. If$ARGUMENTScontains--coverage, include it as well. -
Parse the output. The validator checks:
- No duplicate endpoint
names (operationId collisions in OpenAPI) - No duplicate
METHOD pathcombinations - Every endpoint declares at least one response
- Every
response body matches <ModelName>assertion references a model that exists in the router - Endpoints inside a bounded context only use models declared in that context's
models[]
- No duplicate endpoint
-
For each finding, propose a specific fix:
Duplicate endpoint name
Rename the newer endpoint to something unique. OpenAPI uses name as operationId, so collisions produce silent bugs in generated clients.
Duplicate METHOD path
Two endpoints claim the same route. Usually a copy-paste mistake. Merge them or change one path.
Missing response
Every endpoint needs at least one entry in responses. Even a 204 needs responses: { 204: { schema: t.empty(), description: '...' } }.
Unknown model in assertion
A behavior uses 'response body matches Pet' but Pet isn't registered on the router (not reachable from any endpoint's request or response). Either add the model to an endpoint's schemas or rewrite the assertion to a different model.
Bounded-context leak (warning → error in --strict)
An endpoint inside router.context('Pets', { models: [Pet, ...] }) uses a model that isn't in models[]. Either add it to the context's models[] (if it legitimately belongs) or move the endpoint to the right context.
- After fixing, re-run
triad validate --strictto confirm all issues cleared.
Rules
--strictturns warnings into errors — bounded-context leaks fail the build. Use--strictin CI.--coveragewarns about endpoints missing boundary coverage (schema constraints with no test hitting them). Add...scenario.auto()to the endpoint's behaviors to fix.- Validator findings are rarely "just rewrite the code" — usually they surface real modeling bugs. Take each one seriously before suppressing it.
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 · 44 lines · 33 tokens per session scan A 824cd186b770
validate is a command published in the GitHub repository justhamade/triadjs (23 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 553 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.