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/mrjptech/macro-pickle/pickle-describegit clone --depth 1 https://github.com/MrJPTech/macro-pickleWrote 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/mrjptech/macro-pickle/pickle-describe)<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-describe"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-describe.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 | $0.00021 | $0.00435 |
| Opus 5 | $0.00010 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
pickle-describe 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.
What it actually says
/pickle-describe
"Look at" a product photo: OCR foreign text / watermarks to strip, and recommend a faceless
in-use scene — via pnpm describe (describeProduct, scripts/lib/vision.ts). The output
feeds the rest of the pipeline: the recommended scene becomes a brief; the detected text is
what to strip when regenerating owned references. Supabase-free.
Usage
- Describe:
pnpm describe <image> --title "<product>" --brand "<store/style>"→ JSON incl.detected_text(to strip),suggested_scene(a faceless in-use moment), and product attributes. --paddleadds the local PaddleOCR sidecar — high-recall small/CJK text + per-line geometry in separateocr_*fields (needs Python +paddleocr; non-fatal if absent). Note:ocr_*fields are not consumed downstream yet (the rail is laid for future in-place watermark masking) —--paddledoesn't change generated output today.- Use the output:
suggested_scene→ the lifestyle scene for /pickle-ref or a UGC brief (/pickle-ugc).detected_text→ the text to STRIP when regenerating clean owned refs.
Notes
- One Gemini vision call per image (paid-eligible) — fine ad-hoc; image quota is separate from
Veo's. For a reference clip use /pickle-ref; to mirror a competitor video use
pnpm analyze-video.
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 · 33 lines · 21 tokens per session scan A 5ef1430e84d2
pickle-describe is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 435 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.