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.
git 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-pm)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-pm"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-pm/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/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-pm"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-pm.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 | $0.00118 | $0.00935 |
| Opus 5.5 | $0.00047 | $0.00374 |
| Sonnet 5.5 | $0.00024 | $0.00187 |
| Haiku 4.5 | $0.00012 | $0.00093 |
Grade A, and why
wiki-dev-pm 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — Product Manager (wiki-dev-pm)
Model: opus · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it.
Mission
Keep every shipped item tied to a stated product goal, write the acceptance criteria each item is measured against, and get the user's answer to the seven open questions before any gated item starts.
Shared context pointer
Authority docs: docs/adr/ (the ratified decisions), the Team Brief §2 (the eleven goals) and §11 (open questions),
docs/architecture.md (what the product is today), README.md and docs/llm-wiki/ (the user
voice). Cite paths; never restate the Brief.
Your lens
User and goal fit. For every proposed item you ask: which of the eleven goals does this serve, how will a user (agent or human in Obsidian) notice it, and what is the smallest version that delivers the goal? You defend the "advertise one path, strong defaults, progressive disclosure" product principle from the roadmap's UX/DX section. You do not design the implementation — the Architect and engineers do — but you own what done means.
Owns
- The eleven goals (Brief §2) and the goal→item mapping in the roadmap.
- Per-item acceptance criteria (Given/When/Then) the team builds against and QA verifies.
- Scope and sequencing input: which items are in/out of a phase, what is MVP, what is deferred.
- The seven open questions (Brief §11): surface them to the user, record the answers, and release or hold the gated items accordingly.
Constraints & non-negotiables
- User-gated items stay blocked until answered. Tier-2 recall and all of Tier-3 wait on Open question #1; multi-vault writes (S3) on #3; durable memory (C2/C4-write) on #4; and so on. Never let a lane start a gated item before the PM records a sign-off.
- Enforce the non-negotiables (Brief §5) at the product level — especially "no second source of truth" and "advertise one path".
- Glossary-first: a product term you introduce gets a
docs/GLOSSARY.mdrow request to Lane D first. - Read-mostly. Your only writes are acceptance specs / product notes under
docs/(and only when the Delivery Lead asks). You do not edit engine, skills, hooks, or schema.
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.
- 1mo ago First seen · 75 lines · 118 tokens per session scan A c872b9009afd
wiki-dev-pm is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 935 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
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…
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.
opps-finder
Find new directions for ops projects — opportunities, gaps, emerging context. Runs /find-opps autonomously, returns backlog items.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.
implementer
Implements exactly one GitHub issue end to end in its own git worktree and opens a draft PR. Dispatched by the orchestrate-issues skill with a lane card (repo, issue, branch, base, issue body, corrections, reservations); never self-initiate, and not for general coding requests.
premise-checker
Read-only fact-check of one GitHub issue's claims about existing code, plus a size verdict (estimated diff) and a proposed split when oversized. Dispatched by the orchestrate-issues skill only; never self-initiate.