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 asfbay-bit/opchain-skills --skill oc-qa-opsgit clone --depth 1 https://github.com/asfbay-bit/opchain-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/asfbay-bit/opchain-skills/oc-qa-ops)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-qa-ops"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-qa-ops/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/asfbay-bit/opchain-skills/oc-qa-ops"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-qa-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00259 | $0.02980 |
| Opus 5.5 | $0.00104 | $0.01192 |
| Sonnet 5.5 | $0.00052 | $0.00596 |
| Haiku 4.5 | $0.00026 | $0.00298 |
Grade A, and why
oc-qa-ops 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Ops
On first invocation, read references/orchestrator.md and follow its welcome protocol.
QA Ops owns the strategy layer of testing: what tests should exist, at which level of the pyramid, with what coverage, verifying which contracts, under what load. It does not run tests — oc-bug-check does that at the commit gate, CI does it on every PR, and oc-scale-ops executes load tests. QA Ops decides what those runners should be running.
The one-sentence split: oc-bug-check answers "do the tests pass?"; oc-qa-ops answers "are these the right tests?"
Command Reference
QA OPS COMMANDS
/oc-qa Show this menu
/oc-qa pyramid Design (or redesign) the test pyramid for this repo
/oc-qa coverage Set or revise coverage budgets
/oc-qa contracts Build the contract-test matrix
/oc-qa loadplan Plan load tests: scenarios, SLOs, targets
/oc-qa audit Gap-audit the existing suite against the pyramid
/oc-qa status Show current strategy + last audit verdict
/checkpoint Show oc-qa-ops checkpoint
/oc-qa pyramid
Design the test pyramid for the repo at hand. Not a lecture on testing theory — a concrete, repo-specific allocation:
- Inventory what exists. Test framework(s), suite shape, counts per level, runtime per level, CI wiring. Read the oc-app-architect and oc-api-dev checkpoints for what the system is supposed to do.
- Declare the levels for THIS repo (typical: unit / integration / contract / e2e — but a CLI tool, a Worker, and a data pipeline get different pyramids). For each level: what belongs there, what must NOT be tested there, target runtime, and which gate runs it (commit gate / CI / nightly).
- Allocate. Where should new tests for a given change land by default? The pyramid answers this mechanically ("handler logic → unit; route wiring → integration; cross-service shape → contract; user flow → e2e, sparingly").
- Anti-pattern rules. Name the repo's specific test smells (snapshot tests of volatile output, e2e tests that restate unit assertions, mocks of code you own) so the build loop's Evaluator can cite them.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +10 lines 75d04323a9f3
- 26d ago Changed 70903fb29925
- 29d ago Changed 897822e8a8ff
- 1mo ago Changed cc387bc9d4a7
- 1mo ago Changed · +8 lines 54cce46243af
- 1mo ago First seen · 223 lines · 259 tokens per session scan A 53a00e53bbf3
oc-qa-ops is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 259 tokens to every session and 2,980 once invoked, about $0.0010 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…