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/wallneradam/cc-plugin-counterpoint/counterpointnpx skills add wallneradam/cc-plugin-counterpoint --skill counterpointgit clone --depth 1 https://github.com/wallneradam/cc-plugin-counterpointWrote 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/wallneradam/cc-plugin-counterpoint/counterpoint)<a href="https://agentmods.dev/skills/wallneradam/cc-plugin-counterpoint/counterpoint"><img src="https://agentmods.dev/badge/skills/wallneradam/cc-plugin-counterpoint/counterpoint.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 | $0.00109 | $0.02736 |
| Opus 5 | $0.00055 | $0.01368 |
| Sonnet 5 | $0.00022 | $0.00547 |
| Haiku 4.5 | $0.00011 | $0.00274 |
Grade A, and why
counterpoint 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 4d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Counterpoint — Collaborative Review with Codex
When to invoke
Only when the user explicitly asks. Examples:
/counterpoint <proposal>— critique mode/consult <question>— consult mode/counterpoint:review— review mode (code review of the local git state)- "Ask Codex what it thinks", "Get a second opinion", "Run this by Codex", "Have Codex review this"
That's it. Do NOT invoke:
- Before finalizing plans
- Before architectural decisions
- When you sense a tradeoff
- Because the situation "feels" non-trivial
If the user did not ask, do not invoke.
What Codex is — and is not
Codex is a source of outside perspective, not an authority. In critique and consult modes it sees only what you put in the prompt; in review mode it inspects the repository itself (read-only). Either way, its observations are hypotheses for you to validate against the actual code — not verdicts to apply.
| MCP tool | Purpose |
|---|---|
mcp__counterpoint__critique |
Review a concrete proposal |
mcp__counterpoint__consult |
Think through an uncertain problem |
mcp__counterpoint__review |
Code review of the local git state (structured findings) |
mcp__counterpoint__status |
Check the active thread and auto-consult state |
mcp__counterpoint__reset |
Clear the thread (rare) |
mcp__counterpoint__consult_on |
Turn on auto-consult mode (set via /consult_on) |
mcp__counterpoint__consult_off |
Turn off auto-consult mode (set via /consult_off) |
Always use these MCP tools directly. Do NOT substitute codex-rescue or any other Codex agent — those create disconnected one-shot sessions and lose the thread memory that makes counterpoint useful.
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.
- 4d ago First seen · 192 lines · 109 tokens per session scan A 087a8f96eb1f
counterpoint is a skill published in the GitHub repository wallneradam/cc-plugin-counterpoint (2 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 2,736 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…