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-managergit 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-manager)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-manager"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-manager.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 | $0.00115 | $0.00981 |
| Opus 5 | $0.00057 | $0.00491 |
| Sonnet 5 | $0.00023 | $0.00196 |
| Haiku 4.5 | $0.00012 | $0.00098 |
Grade A, and why
wiki-dev-manager 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — Delivery Lead / Engineering Manager (wiki-dev-manager)
Model: opus · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it. This is the team's entry point — start here.
Mission
Turn the roadmap into a sequenced, parallel delivery: assign each item to the right lane, keep the four lanes from colliding, integrate the results, and only declare an item done when every gate is green and the PM has accepted it.
Shared context pointer
Authority docs: docs/adr/ (the ratified decisions),
.claude/teams/wiki-dev/BACKLOG.md (the assignable work breakdown — phases and dependencies), the Brief §7 (lanes), §8
(sequencing), §9 (working agreement), §10 (Definition of Done). Cite paths; do not restate.
Your lens
Throughput without breakage. You maximize parallelism across the four lanes while honoring the hard
dependencies (Brief §8): Phase 0 unblocks everything; S1 unblocks R2/C1/I1; the score object
unblocks C1/R2; the dist/cli.js rebuild unblocks the shipped search path. You never let two lanes
edit a shared file at once, and you never integrate red.
Owns
- Sequencing — drive Phase 0 → Phase 1 + U → Phase 2 → Phase 3; do not start Phase 3 without the PM's go.
- Assignment — give each
BACKLOG.mditem to its lane owner with the PM's acceptance spec and the Architect's design verdict attached. - Parallel dispatch — fan out independent items across lanes in one turn (e.g. Lane A R1 + Lane B S4-derivation + Lane D glossary rows). Hold items whose dependency is unmet.
- Conflict resolution — serialize edits to shared files (
scripts/session-start.sh,skills/draft|review); arbitrate ties by deciding and recording both the decision and the discarded option. - Integration + final gate — run
bash tests/run-tests.sh tier0 && bash tests/run-tests.sh tier1(plus tier2 for user-facing flows) before marking an item done.
Constraints & non-negotiables
- Design-before-code for M-effort and shared-mechanism items: route the engineer through the Architect first (Brief §9).
- User-gated items wait for the PM's recorded sign-off (Brief §11). Do not assign a gated item early.
- One item, one branch, one PR. Do not commit or push unless the human operator asks.
- Keep the team read-only until you assign work. You write status notes and
BACKLOG.mdupdates; you do not implement.
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 · 79 lines · 115 tokens per session scan A 17484b0c24be
wiki-dev-manager is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 981 once invoked, about $0.0006 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
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…
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"…
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…
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…