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 skills/boshu2/agentops/testnpx skills add boshu2/agentops --skill testgit clone --depth 1 https://github.com/boshu2/agentopsWhat 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 | $0.00025 | $0.02447 |
| Opus 5 | $0.00013 | $0.01223 |
| Sonnet 5 | $0.00005 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00245 |
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Skill
Generate real tests, run them, and leave reproducible coverage or TDD evidence.
Do not stop at a plan unless the requested mode is strategy.
Critical Constraints
- Why: behavior is the contract. Derive tests from acceptance scenarios and public behavior, not implementation details or coverage percentages alone.
- Why: prove new behavior. In TDD mode record a real failing test before the minimal implementation; a test that starts green is not RED evidence.
- Why: avoid false confidence. Assert exact values, error types/messages, and branch outcomes; ban zero-assertion, tautological, and padding tests.
- Why: keep suites trustworthy. Tests must be deterministic, isolated, and independent of timing, ordering, production services, or mutable shared state.
- Why: protect user intent. Report a product bug discovered by a test; do not silently change product behavior or delete existing tests without approval.
- Why: close with proof. Run the narrow test after each edit, then the relevant suite and coverage command before handing work downstream.
Modes
| Mode | Use when | Required result |
|---|---|---|
generate |
writing tests for existing code | passing focused and suite tests |
coverage |
finding and filling important gaps | before/after coverage plus tests |
tdd |
implementing new behavior test-first | logged RED → green → refactor cycles |
strategy |
designing test architecture only | inventory, risks, and recommendations |
Default to generate. Flags: --mode, --scope, --min-coverage, and
--dry-run narrow the workflow but never weaken its evidence requirements.
Oracle-strength hierarchy
Every test asserts through an oracle, and oracles are not equal. Rank them:
exact value > property/invariant > differential (two implementations agree) > smoke (it ran)
Choose the strongest oracle the behavior admits and name the oracle-strength
tier when a test uses anything below exact. A smoke assertion where an exact one was available
is the oracle downgrade failure mode: the test runs the code but proves
almost nothing about it. Stop condition: no acceptance scenario may be covered
only by smoke-tier tests when a stronger oracle is practical; if only smoke is
practical (e.g. nondeterministic external output), record why in
.agents/scratch/tests/summary.md so the gap is a visible decision, not an accident.
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 · 244 lines · 25 tokens per session scan A 4ec3f028660c
test is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,447 once invoked, about $0.0001 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 skills, from other repositories
brainstorm
Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
commit-push-pr
Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
doubt-driven
Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.