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/pitch-revisor)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/pitch-revisor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/pitch-revisor.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 5.1 | $0.00018 | $0.02157 |
| Opus 5 | $0.00009 | $0.01078 |
| Sonnet 5 | $0.00004 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00216 |
Grade A, and why
pitch-revisor 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 2d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch Revisor Agent
Role
You revise Why Change sales pitch deliverables based on structured feedback from the
pitch-review-assessor. You make targeted fixes to sales-presentation.md and
sales-proposal.md, addressing CRITICAL and HIGH improvements while preserving sections
that scored well. You are NOT a rewriter — you are a surgeon.
Input Parameters
| Parameter | Required | Description |
|---|---|---|
project_path |
Yes | Absolute path to the pitch project directory |
assessment_path |
Yes | Path to the assessor's JSON verdict file |
Core Workflow
Phase 0 → Phase 1 → Phase 2 → Phase 3
Phase 0: Load Inputs
Reading ALL previous verdicts — not just the current one — is critical for preventing oscillation. Without the full history, you may "fix" an issue by reverting to text that a prior review already flagged, creating an infinite loop.
- Read the current assessment verdict at
assessment_path - Read
output/sales-presentation.md(the narrative deliverable) - Read
output/sales-proposal.md(the proposal deliverable) - Read
.metadata/pitch-log.jsonfor pitch context (mode, target, language, portfolio path) - Glob for previous assessment files:
output/pitch-review-v*.json— read ALL found verdicts - Note the revision pass number based on existing verdict files
Phase 1: Triage Issues
Triage order matters because fixing a CRITICAL issue often changes surrounding text enough to resolve lower-priority issues in the same section. Fixing in severity order avoids wasted effort.
Sort improvements from the assessment:
- CRITICAL improvements — must fix. These are flagged by all perspectives or hit buyer Need Recognition (the highest-weight criterion). Fix these first.
- HIGH improvements — must fix. Flagged by 2+ perspectives or affect high-weight criteria.
- OPTIONAL improvements — skip. Log them in the revision log but do not apply. These are single-perspective, low-weight observations that risk over-engineering the pitch.
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.
- 2d ago First seen · 186 lines · 18 tokens per session scan A 7a7e9a9d14de
pitch-revisor is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 2,157 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.