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 skills/cogni-work/insight-wave/knowledge-indexnpx skills add cogni-work/insight-wave --skill knowledge-indexgit clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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/cogni-work/insight-wave/knowledge-index)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-index"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-index.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 | $0.00217 | $0.04055 |
| Opus 5 | $0.00109 | $0.02027 |
| Sonnet 5 | $0.00043 | $0.00811 |
| Haiku 4.5 | $0.00022 | $0.00405 |
Grade A, and why
knowledge-index 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 yesterday.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Index
Three related operations on a bound knowledge base, all delegating to the locked
renderers (sub_index.py, root_index.py) so index-shaping logic lives in one
place:
- Rebuild — deterministically (re)render the six per-type sub-indexes
(
wiki/<type>/index.md) and the curated root MAP (wiki/index.md) from current wiki state. Useful after manual page edits, a crashed finalize, or any time the indexes look stale. Idempotent: an unchanged wiki re-renders byte-identically. - Migrate — converge an EXISTING old-structure wiki (
schema_version < 0.0.8) onto the curated layoutknowledge-setupseeds for new ones: control files relocate intowiki/meta/, theoverview.mdnarrative folds into theindex.mdintro, the flat root index splits into root-map + per-type sub-indexes, and the schema bumps to0.0.8. Dry-run first, always. - Repair — on a base already on the curated layout (
schema_version >= 0.0.8), regenerate drifted machine-owned regions keyed on the structural-drift classhealth.pyemits (not the version floor): a theme-scopedROOT-LINKSspan stuck on the empty-state sentinel is re-rendered viaroot_index.py render, and a laggingschema_versionis reconciled to the current engine schema. Same dry-run-first /--applyergonomics as migrate. Idempotent: a non-drifted, current-schema base is anoop. Scope boundary: the script repairs ROOT-LINKS + schema lag; a degraded OVERVIEW-NARRATIVE (stuck on the bootstrap placeholder) is re-authored by a separate orchestrator step (see 2c) —root_index.py rendercarries that block verbatim and never re-authors it.
The migrate split is the lossy transform — human content could be dropped when
the flat root becomes a MAP. It is delegated to root_index.py render, which
carries every MACHINE-OWNED:PORTAL-LEADIN span and every human
(non-sentineled) lead-in verbatim and drops only the per-page bullets (they
relocate into the sub-indexes). The migrator never re-implements the split.
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.
- yesterday Changed dbf2a98ab639
- 5d ago First seen · 282 lines · 217 tokens per session scan A c259c991849d
knowledge-index is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 217 tokens to every session and 4,055 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…