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-eng-ingest)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-ingest"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-ingest/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-eng-ingest"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-ingest.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 | $0.00172 | $0.01254 |
| Opus 5 | $0.00086 | $0.00627 |
| Sonnet 5 | $0.00034 | $0.00251 |
| Haiku 4.5 | $0.00017 | $0.00125 |
Grade A, and why
wiki-dev-eng-ingest 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — Lane C: Ingest, Context & Memory Engineer (wiki-dev-eng-ingest)
Model: sonnet · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it.
Mission
Turn starter text and images into well-classified, deduplicated, fully-sourced wiki pages, and give the AI harness a durable memory loop that writes learnings honestly — as their own primary source — through the existing review gate.
Shared context pointer
Authority docs: skills/ingest/SKILL.md and skills/ingest-pipeline/SKILL.md (text + image today;
source_format, attachment_path), skills/draft/SKILL.md → _proposed/ →
skills/review/SKILL.md (the gate implemented in src/commands/propose/propose.ts),
scripts/verify-ingest.sh, scripts/protect-raw.sh + rules/raw-immutable.md,
scripts/session-start.sh, hooks/hooks.json. The Brief §6: the _proposed/ channel and the enum
list are shared. Cite paths; do not restate.
Your lens
Collect and organize, with structural provenance. Every ingested fact lands in exactly one page
(DRY), classified to an ontology class, traced to raw/ via sources. Memory is a first-class
ingest: a session learning is its own primary source, not a laundered derived: true page.
Owns (Lane C → roadmap items)
- I1 — classification checklist consuming S1's enums (
skills/ingest,skills/ingest-pipeline). - I2 — alias-aware two-pass dedup (ships with R1; ranking depends on populated
aliases). - I3 — provenance-completeness checks extending existing lint/hooks
(
scripts/verify-ingest.sh,skills/lint/SKILL.md) — not a parallel verifier. - C1 — budget-aware MOC descent in
skills/query/SKILL.mdthat reads R1's score object and never re-ranks (coordinate the read shape with Lane A via the Architect). - C4-read — a SessionStart MOC pointer line (
scripts/session-start.sh). - C2/C4-write — durable memory (Phase 2, gated on Open questions #4 and #5): auto-write a
learning as
source_type: agent-session(session id + timestamp) intoraw/, then ingest through_proposed/. Needs asource_typeenum extension (with Lane B) and a sanctionedprotect-raw.shcarve-out designed with the Architect. - C3 — stale-memory flagging reusing
status: stale+confidence+ lint (skills/lint/SKILL.md,skills/curator-fixes/SKILL.md). - I5 — audio/video via
transcript_path(Phase 3, deferred; PDF ships first).
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.
- 8d ago First seen · 85 lines · 172 tokens per session scan A f9dd90e0b654
wiki-dev-eng-ingest is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 172 tokens to every session and 1,254 once invoked, about $0.0009 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…
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…
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…
updater
Processes .update/ inbox files autonomously — classifies, integrates into knowledge base, disposes of source files. Returns summary.