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 skills add antithesishq/antithesis-skills --skill test-triagegit clone --depth 1 https://github.com/antithesishq/antithesis-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/antithesishq/antithesis-skills/test-triage)<a href="https://agentmods.dev/skills/antithesishq/antithesis-skills/test-triage"><img src="https://agentmods.dev/badge/skills/antithesishq/antithesis-skills/test-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/antithesishq/antithesis-skills/test-triage"><img src="https://agentmods.dev/badge/skills/antithesishq/antithesis-skills/test-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00092 | $0.02437 |
| Opus 5 | $0.00046 | $0.01218 |
| Sonnet 5 | $0.00018 | $0.00487 |
| Haiku 4.5 | $0.00009 | $0.00244 |
Grade A, and why
test:triage scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Reaching for the web UI / agent-browser / `curl` against the report URL How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test: Antithesis Triage Skill
End-to-end test harness for the antithesis-triage skill. Spawn sub-agents
that perform real triage operations against the live Antithesis API via
snouty, then review their work for issues.
The top-level agent MUST NOT use the antithesis-triage skill directly. All triage operations happen inside sub-agents. The top-level agent only orchestrates and reviews.
Prerequisites
Before starting, verify the same prerequisites the triage skill requires:
which snouty && which jq && snouty --version
snouty must be at least version 0.6.0. Then confirm credentials with the canonical check (same as the triage skill's preflight):
snouty doctor
If any prerequisite is missing, out of date, or snouty doctor fails, stop and
report which ones are unavailable.
Phase 1: Discover Runs
Spawn a general-purpose sub-agent with the Agent tool. Provide these
instructions, replacing {{TENANT}} with the actual value of the
$ANTITHESIS_TENANT environment variable and {{TRIAGE_SKILL}} with the
absolute path to antithesis-triage/SKILL.md in this repository. If
$ANTITHESIS_TENANT is empty in the current shell, ask the user for the tenant
name instead of aborting.
Read the skill file at {{TRIAGE_SKILL}} and follow its instructions to list
recent runs for the tenant "{{TENANT}}". Follow the "Summarize recent runs"
workflow.
Return the COMPLETE raw NDJSON of `snouty runs --json list -n 200` along
with a per-run summary that includes, for each run:
- run_id
- status
- launcher
- created_at / completed_at
- antithesis.test_name and antithesis.description (from parameters)
- whether links.triage_report is present (triageable yes/no)
Do NOT filter by status — return the full list so the orchestrator can
select targets across statuses.
Wait for this sub-agent to finish before proceeding.
If the sub-agent did not return the NDJSON list, abort.
Phase 2: Select Test Targets
Read the sub-agent output. From the run listing, select two targets:
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.
- 12d ago First seen · 260 lines · 92 tokens per session scan A 6b0bb123b1d5
test:triage is a skill published in the GitHub repository antithesishq/antithesis-skills (267 stars, last pushed 3d ago), licensed Apache-2.0. It adds 92 tokens to every session and 2,437 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.