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 instructions/cogni-work/insight-wave/claude-mdgit 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/instructions/cogni-work/insight-wave/claude-md)<a href="https://agentmods.dev/instructions/cogni-work/insight-wave/claude-md"><img src="https://agentmods.dev/badge/instructions/cogni-work/insight-wave/claude-md.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 | $0.08734 | $0.08734 |
| Opus 5 | $0.04367 | $0.04367 |
| Sonnet 5 | $0.01747 | $0.01747 |
| Haiku 4.5 | $0.00873 | $0.00873 |
Grade A, and why
insight-wave CLAUDE.md 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
insight-wave
8-plugin monorepo for consulting, sales, and marketing on Claude Code. Apache-2.0. All plugins follow the Claude Code plugin standard. The roster and its count are single-sourced from .claude-plugin/marketplace.json plugins[] — when the roster changes, update every count stated elsewhere in this repo from it.
Repo Structure
insight-wave/
├── .claude-plugin/marketplace.json Marketplace manifest (8 plugins)
├── cogni-{name}/ Each plugin directory
│ ├── .claude-plugin/plugin.json Plugin manifest (name, version, description)
│ ├── README.md Plugin documentation (IS/DOES/MEANS messaging)
│ ├── CLAUDE.md Developer guide (architecture, data model, conventions)
│ ├── skills/{skill-name}/SKILL.md Skill definitions
│ ├── agents/{agent-name}.md Agent definitions
│ ├── commands/{command-name}.md Slash command definitions
│ ├── hooks/ Event-driven hooks (optional)
│ ├── output-styles/ Voice/style registers, auto-discovered in /config (optional)
│ ├── scripts/ Utility scripts (bash + python3, stdlib only)
│ └── references/ Framework docs, schemas, templates
├── docs/ User documentation (generated by cogni-docs)
│ ├── getting-started.md
│ ├── ecosystem-overview.md
│ ├── plugin-guide/{name}.md Per-plugin deep dives (one per plugin, generated by cogni-docs)
│ ├── workflows/*.md Cross-plugin pipeline guides (7 workflows)
│ ├── architecture/ Design philosophy, plugin anatomy, ER diagram
│ └── contributing/ Plugin development guide
└── assets/ Architecture diagram (Excalidraw + SVG)
Generated documentation artifacts
The repo-wide documentation-drift audit belongs at docs/audit-report.md — that is the single home for audit output, and it is replaced wholesale by a fresh cogni-docs audit run rather than hand-edited. A stale header there means the audit is due to be re-run, not patched by hand. .claude-plugin/ holds the marketplace manifest and nothing else. An older drift report once sat at .claude-plugin/doc-audit-report.md and was removed rather than regenerated: nothing in this repo referenced or wrote that path, docs/audit-report.md supersedes it, and its plugin roster predated the current marketplace by several retirements. Do not add a report back under .claude-plugin/.
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 · +4 lines · +1,618 tokens per session ea50b9e8a377
- 5d ago First seen · 197 lines · 7,116 tokens per session scan A ee79f5d164fe
insight-wave CLAUDE.md is an instructions file published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 8,734 tokens to every session, about $0.0437 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.