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 commands/wallneradam/cc-plugin-counterpoint/consult_ongit 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/commands/wallneradam/cc-plugin-counterpoint/consult_on)<a href="https://agentmods.dev/commands/wallneradam/cc-plugin-counterpoint/consult_on"><img src="https://agentmods.dev/badge/commands/wallneradam/cc-plugin-counterpoint/consult_on.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 | $0.00013 | $0.00409 |
| Opus 5 | $0.00006 | $0.00204 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
consult_on 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.
What it actually says
Enable auto-consult by calling the mcp__counterpoint__consult_on MCP tool.
Auto-consult mode is now ACTIVE. From this point forward, until the user runs /consult_off, the following rules apply for the rest of this conversation:
- Before every implementation plan, design decision, or significant code change, call
mcp__counterpoint__consultwith your proposed approach. - Before every architectural choice or non-trivial trade-off, call
mcp__counterpoint__critiquewith the concrete proposal. - Exceptions (no consultation needed):
- Trivial single-line edits (typos, formatting, mechanical renames)
- Direct execution of an already-consulted plan
- When the user explicitly says "skip" or "just do it" for a specific action
- When in doubt, consult. It is better to over-consult than to miss something.
- Keep each consultation focused — send the key decision and minimal context, not every detail. Multi-round is the point; build up over rounds, don't front-load.
- All other counterpoint rules still apply: summarize Codex's response in chat after every round (the user does not see raw MCP output), defend your position against generic/theoretical points, strip out unrequested workstream/phase framing, and pursue multi-round dialogue when there is real disagreement. See the
counterpointskill for the full protocol. - Do NOT delegate to
codex-rescueor any other Codex agent — those bypass the persistent thread.
This is a PERSISTENT instruction for this session. Check the current state at any time with mcp__counterpoint__status.
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 · 22 lines · 13 tokens per session scan A e5fe77107d49
consult_on is a command published in the GitHub repository wallneradam/cc-plugin-counterpoint (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 409 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.