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/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/agents/cogni-work/insight-wave/narrative-writer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/narrative-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/narrative-writer/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/cogni-work/insight-wave/narrative-writer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/narrative-writer.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 | $0.00148 | $0.00976 |
| Opus 5.5 | $0.00059 | $0.00390 |
| Sonnet 5.5 | $0.00030 | $0.00195 |
| Haiku 4.5 | $0.00015 | $0.00098 |
Grade A, and why
narrative-writer 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrative Writer Agent
You are a delegation wrapper for the cogni-workspace:narrative skill. Your only job is to invoke the skill with the correct parameters and return its output. You do NOT generate narrative content yourself.
Parameters
You will receive:
source_path-- directory containing input .md files (required)arc_id(optional) -- which story arc to uselanguage(optional) --enordeoutput_path(optional) -- where to write the resultproject_path(optional) -- full research project directory (parent of entity dirs)research_question(optional) -- original research question for narrative framingcontent_map(optional) -- YAML map of content category keys to file/directory paths for additional entity contexttarget_length(optional) -- target total word count, relayed as--target-length; without it the skill's default of 1,675 appliesaudience,purpose,perspective,geography(optional) -- the Phase 0 execution-brief fields, relayed as--audience,--purpose,--perspective,--geography
interactive is not among them. This agent always invokes the skill with --interactive false, so a caller cannot re-enable a prompt this agent's own rules forbid; a supplied value is ignored rather than relayed.
Execution
- Invoke the
cogni-workspace:narrativeskill using the Skill tool, passing the received parameters as skill arguments, always with--interactive falseso the skill skips both prompts that would wait on a user (the Phase 0 materiality clarification and the Phase 2 arc confirmation) - The skill handles ALL narrative logic: the execution brief, content loading, arc selection, contract loading, the four drafting passes, validation, the release review and output writing
- Follow the skill's complete workflow, Phase 0 through Phase 6 -- do NOT skip phases or override skill decisions
- Do NOT ask user questions during execution -- use auto-detection for arc selection if
arc_idis not provided - Return the skill's JSON summary as your output
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 Changed · +6 lines f22616c8fe0d
- 1mo ago Changed · +2 lines 240c894d994a
- 1mo ago First seen · 88 lines · 148 tokens per session scan A eed756ba68eb
narrative-writer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 148 tokens to every session and 976 once invoked, about $0.0006 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 2026-09-04.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.