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/lckx777/copy-chief-blackWrote 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/lckx777/copy-chief-black/diagnose-offer)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/diagnose-offer"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/diagnose-offer/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/commands/lckx777/copy-chief-black/diagnose-offer"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/diagnose-offer.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 | $0.00013 | $0.01539 |
| Opus 5 | $0.00006 | $0.00770 |
| Sonnet 5 | $0.00003 | $0.00308 |
| Haiku 4.5 | $0.00001 | $0.00154 |
Grade A, and why
diagnose-offer 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 11d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose Offer — Cross-System Quality Audit
Arguments: $ARGUMENTS
Step 1: Locate the Offer
Extract offer name from $ARGUMENTS. Search for the offer directory:
find ~/copywriting-ecosystem -maxdepth 3 -name "helix-state.yaml" 2>/dev/null
Match the offer name (case-insensitive, partial match OK) to find the offer root path.
If no match found, list available offers and ask the user to clarify.
Step 2: Run 5 Diagnostic Checks
For each check, assign a status: PASS (green), WARN (yellow), or FAIL (red).
Check 1: VOC Quality
Read {offer}/research/synthesis.md and {offer}/research/voc/summary.md.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| synthesis.md exists | Yes | — | No |
| Confidence score | >= 80% | 70-79% | < 70% or missing |
| Platforms with quotes | 4+ | 2-3 | 0-1 |
| Total quotes | 100+ | 50-99 | < 50 |
| DRE defined | Yes, with escalada | Mentioned but vague | Missing |
| Emotions categorized | 5+ categories | 3-4 | < 3 |
Score: Count PASS=2pts, WARN=1pt, FAIL=0pts. Max 12. Normalize to /10.
Check 2: MUP/MUS Quality
Read {offer}/mecanismo-unico.yaml.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| File exists | Yes | — | No |
| State | APPROVED | VALIDATED | DRAFT/UNDEFINED |
| MUP nova_causa filled | Yes, specific | Generic | Empty |
| MUP sexy_cause filled | Yes, transmissible | Exists but weak | Empty |
| MUS gimmick_name filled | Yes, sticky | Exists but weak | Empty |
| MUS origin_story filled | Yes, with paradox | Exists but generic | Empty |
| MUS authority_hook filled | Yes, super structure | Exists but weak | Empty |
| RMBC avg score | >= 8 | 7-7.9 | < 7 or missing |
Score: Count PASS=2pts, WARN=1pt, FAIL=0pts. Max 16. Normalize to /10.
Check 3: Copy Quality (Production Gates)
Read {offer}/helix-state.yaml for tools_used in production phase. Check for validation scores.
| Criterion | PASS | WARN | FAIL |
|---|---|---|---|
| blind_critic used | Yes, score >= 8 | Used, score < 8 | Not used |
| emotional_stress_test used | Yes, score >= 8 | Used, score < 8 | Not used |
| layered_review used | Yes | — | Not used |
| black_validation used | Yes, score >= 8 | Used, score < 8 | Not used |
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.
- 11d ago First seen · 185 lines · 13 tokens per session scan A 23db743d15c7
diagnose-offer is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 1,539 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.