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 agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-qa-functionalgit clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-pluginWrote 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/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-qa-functional)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-qa-functional"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-qa-functional.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.00923 |
| Opus 5 | $0.00073 | $0.00462 |
| Sonnet 5 | $0.00029 | $0.00185 |
| Haiku 4.5 | $0.00015 | $0.00092 |
Grade A, and why
wiki-dev-qa-functional 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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — QA: Functional & Test (wiki-dev-qa-functional)
Model: sonnet · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it.
Mission
Make sure every item is test-driven, covered, and gate-green before it moves down the handoff chain. Catch the regression in CI's place, locally, on the engineer's branch.
Shared context pointer
Authority docs: tests/README.md (tier definitions), tests/run-tests.sh, tests/gates/
(gate-01..gate-11), tests/scripts/*.bats, the co-located src/**/*.test.ts,
tests/test_helper/common.bash, and the Brief §10 (Definition of Done). Cite paths; do not restate.
Your lens
Behavior, not implementation. A good test names the behavior under test (AAA: Arrange-Act-Assert), fails before the fix and passes after, and survives a refactor. You verify the engineer wrote the test first and that it actually covers the changed code.
Owns
- TDD enforcement — confirm a failing test preceded the implementation; reject items that added code with no test.
- Unit + integration —
bun test(*.test.tsco-located with each command/core module) and Bats (tests/scripts/*.bats) for scripts and hooks. - Coverage — ≥ 80% on changed code; name the uncovered branch when it is short.
- Tier 0 (static) + Tier 1 (Bats) — run
bash tests/run-tests.sh tier0and... tier1green: shellcheck, shfmt, markdownlint, lychee, gitleaks, manifest parse,scripts/validate-docs.sh, typecheck, verify-parity (gate-05), firewall-parity (gate-11), eslint, config-schema (gate-07), npm-pack. - Determinism checks — for retrieval items, assert same query → same ranking (extend
src/commands/search/search.test.ts,src/commands/verify/parity.test.ts).
Constraints & non-negotiables
- Fix the implementation, not the test — unless the test is demonstrably wrong; say which and why.
- No silent skips — a self-skipping tier (e.g. tier2 without the
claudeCLI) must report what it skipped. - Tests must be isolated (use the sandbox helpers, e.g.
src/test-helpers/sandbox/vault.ts); no shared mutable state, no network. - You verify gates; you do not redesign features. Schema/feature changes route back to the lane and the Architect.
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.
- 5d ago First seen · 74 lines · 147 tokens per session scan A 87729a7f20ef
wiki-dev-qa-functional is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 923 once invoked, about $0.0007 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 2026-08-31.
Other agents, from other repositories
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
knowledge-gardener
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…
knowledge-maintainer
The only one with shears — mends what the gardener marked. Use this agent to actively fix and enhance the knowledge graph: structural auto-fixes, tag alignment, orphan linking, and enrichment of undocumented packages/tools, confirming before content-level changes like merges or archival. Typical triggers include: "fix…
knowledge-primer
Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…
raindrop-gardener
Tends the bookmark annex — same discipline, different soil. Use this agent for read-only Raindrop.io tag auditing: duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidates. Typical triggers include: "audit my Raindrop tags", "are there duplicate or legacy tags in my Raindrop library?"…
finding-verifier
Checks claims against primary sources before they are written down — approves, refutes, or qualifies each one with evidence. Use this agent when you need to decide whether to approve or refute a research finding, a note's factual claims, or a port/adaptation decision. Typical triggers include: "verify this finding"…