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/lckx777/copy-chief-black/classifygit 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/classify)<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/classify"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/classify.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 | $0.00000 | $0.01018 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
classify 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/classify — Content Classification
Classify text content into 3 specificity levels for auto-distribution in the copywriting ecosystem. No LLM required — pure signal-based detection.
Usage
# Classify a file
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts <file>
# Classify inline text
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts --text "some text"
# Classify + distribute to target path
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts <file> --distribute
# Dry run (show target without writing)
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts <file> --dry-run
# JSON output (for piping/scripting)
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts <file> --json
# Combine flags
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts <file> --distribute --dry-run
bun run ~/copywriting-ecosystem/scripts/bifurcation.ts --text "content" --distribute --json
Classification Levels
OFFER_SPECIFIC
Content that belongs to a specific offer. Detected by:
- Offer names (florayla, neuvelys, quimica-amarracao, etc.)
- Product/ingredient names (Psyllium Husk, CoQ10, Cristais de Otolitos)
- Expert names tied to an offer (Dr. Klaus Richter, Rafael Mendes)
- Gimmick names / Sexy Causes specific to an offer
- File paths containing
{niche}/{offer}/
Destination: ~/copywriting-ecosystem/{niche}/{offer}/knowledge/ingested.md
NICHE_GENERIC
Content relevant to an entire niche, not a specific offer. Detected by:
- Niche terms (constipação, tinnitus, concurseiro, amarração, etc.)
- Generic avatar patterns (mulheres 45+, concurseiro intermediário)
- Niche names (saude, relacionamento, concursos)
- Generic niche problems without product names
Destination: ~/copywriting-ecosystem/{niche}/biblioteca_nicho_{niche}_CONSOLIDADA.md
UNIVERSAL
Copy principles, frameworks, and expert insights applicable across all niches. Detected by:
- Copy terms (DRE, MUP, MUS, headline, hook, CTA, VSL)
- Framework names (RMBC, HELIX, AIDA, PAS, Logo Test)
- Persuasion principles (specificity, social proof, scarcity, authority)
- Expert names (Schwartz, Halbert, Ogilvy, Makepeace, Sugarman, Kennedy, etc.)
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.
- 5d ago First seen · 109 lines · 0 tokens per session scan A 2000a60979dc
classify is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,018 tokens. 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.