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/scenariogit 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 | $0.00034 | $0.00866 |
| Opus 5 | $0.00017 | $0.00433 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
scenario scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the triad-behaviors skill — it carries the authoritative assertion phrase table, fixture syntax, and scenario.auto() reference. Do NOT invent phrases — unrecognized strings fail as "Unrecognized assertion".
Add behavior scenarios to an existing endpoint or channel based on the user's description ($ARGUMENTS).
Steps
-
Locate the target endpoint or channel. If the user gives a name, grep for
name: 'thatName'. If they describe the resource, find the matching file insrc/endpoints/orsrc/channels/. -
Understand the business intent first. A scenario name should describe business intent, not mechanics:
- Good:
"Duplicate pet names are rejected within the same species" - Bad:
"POST /pets returns 409 when name is taken"
- Good:
-
Write the
.given()stage — seed fixtures via.setup(async services => { return { foo: ... } })if the scenario depends on existing state, or use.fixtures({...})for static values. -
Set the request —
.body(...),.params(...),.query(...),.headers(...). Use{placeholder}tokens to interpolate fixtures (e.g..params({ id: '{petId}' })). -
Write the
.when()narrative — a short string describing the action. This flows to Gherkin but doesn't affect test execution. -
Write the
.then()and.and()assertions — every phrase must match a row in the phrase table (seetriad-behaviorsskill):response status is <N>response body matches <ModelName>response body has <path> "<string>"— double quotes, never singleresponse body has <path> <number>response body has <path> true/falseresponse body has length <N>response body is an arrayresponse body is empty(for 204/t.empty()responses)response body has code "<CODE>"
-
For channels, use channel phrases instead:
<client> receives a <messageType> eventall clients receive a <messageType> event<client> does not receive a <messageType> event<client> receives a <messageType> with <field> "<value>"connection is rejected with code <N>
-
Consider adding
...scenario.auto()at the end of the behaviors array if it's not already there — it generates missing-field/boundary/enum/type scenarios from the schema constraints for free. -
Run
triad test --filter <name>to verify every new scenario parses, seeds correctly, and passes.
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 · 58 lines · 34 tokens per session scan A 2067366ee8bf
scenario is a command published in the GitHub repository justhamade/triadjs (23 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 866 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
git
Git operations with intelligent commit messages and workflow optimization.
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.