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-finalizenpx skills add cogni-work/insight-wave --skill knowledge-finalizegit clone --depth 1 https://github.com/cogni-work/insight-waveWhat 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 | $0.00137 | $0.31871 |
| Opus 5 | $0.00068 | $0.15935 |
| Sonnet 5 | $0.00027 | $0.06374 |
| Haiku 4.5 | $0.00014 | $0.03187 |
Grade C, and why
knowledge-finalize scanned grade C with 2 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "<project_path>/.metadata/verify-shards" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
[`references/finalize-compose-subprocess.md`](../../references/finalize-compose-subprocess.md) How it starts
The opening of the file, as written. The whole thing — 1,148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Finalize
Phase 7 of the inverted pipeline. Reads <project>/output/draft-vN.md + <project>/.metadata/verify-vN.json + <project>/.metadata/citation-manifest.json, runs cycle-guard.py to refuse self-citing loops, deposits the verified draft as <WIKI_ROOT>/wiki/syntheses/<synthesis-slug>.md, runs three cogni-wiki helpers (wiki_index_update.py, config_bump.py, rebuild_context_brief.py) directly at script level, appends a research_projects[] entry to binding.json, writes one ## [YYYY-MM-DD] finalize | … line to wiki/log.md, and runs a Step 10.5 conformance gate (lint_wiki.py --fix=all + health.py) so the deposited base passes cogni-wiki's own structural checks.
This is the inverted-pipeline closing step. Without it, every verified draft lives forever in <project>/output/ and the wiki cannot accumulate cross-source framing — the compounding property that differentiates cogni-knowledge from one-shot deep-research tools requires future knowledge-compose runs to read wiki/syntheses/*.md as prior context. Finalize is what makes that read non-empty.
Synthesis-page frontmatter shape (matches cogni-wiki SCHEMA for type: synthesis per cogni-wiki/CLAUDE.md §"Page Frontmatter"):
---
id: <synthesis-slug>
title: <plan.topic verbatim>
type: synthesis
tags: [synthesis]
created: <today ISO>
updated: <today ISO>
sources:
- wiki://<cited-slug-1>
- wiki://<cited-slug-2>
derived_from_research: <project-slug>
draft_revision_round: <verify.revision_round>
---
derived_from_research is stamped inline (no lineage-stamp.py dispatch — that helper walks raw/research-<slug>/, which inverted-pipeline projects don't write to). draft_revision_round is informational; cogni-wiki's lint allows arbitrary additive frontmatter keys.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 7 — knowledge-finalize" once to anchor on the contract.
When to run
<project>/.metadata/verify-vN.jsonexists for the latestoutput/draft-vN.md(Phase 6 /knowledge-verifyhas run).- User explicitly invokes
/cogni-knowledge:knowledge-finalize.
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.
- 3d ago First seen · 1,148 lines · 137 tokens per session scan C cd746008f592
knowledge-finalize is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 137 tokens to every session and 31,871 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…