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 skills add Marcel-Bich/marcel-bich-claude-marketplace --skill skill-capturegit clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplaceWrote 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/marcel-bich/marcel-bich-claude-marketplace/skill-capture)<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/skill-capture"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/skill-capture/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/skills/marcel-bich/marcel-bich-claude-marketplace/skill-capture"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/skill-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 55 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 115 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 122 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00170 | $0.02031 |
| Opus 5 | $0.00085 | $0.01015 |
| Sonnet 5 | $0.00034 | $0.00406 |
| Haiku 4.5 | $0.00017 | $0.00203 |
Grade A, and why
skill-capture 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-capture - recurring workflow becomes a reusable skill
When the same ordered, multi-step workflow keeps recurring in a session, that repetition is a signal: the workflow is worth capturing once as a Claude Code skill so it need not be re-derived every time. This skill governs how credo notices that repetition and, only with the right permission, turns it into a discoverable skill - without inventing any new infrastructure.
Detection heuristic (in-session, no backend)
Detection is purely heuristic and lives entirely in the current session's context. There is NO persistent counter, NO tracking file that increments, NO new infrastructure. You notice the pattern the same way a person would:
- A candidate is the SAME multi-step sequence - the same ordered steps or commands, small variation allowed (different arguments, paths, or names) - that you have carried out about three times in the running session.
- One-off actions and trivial single commands are not candidates. The value is in a multi-step ordered sequence that you would otherwise reconstruct from scratch each time.
- Detection resets with the session. This skill does not try to remember across sessions via
a counter; cross-session memory lives only in the two
.credo/files below, which are written when a pattern is actually noted or built, never as a running tally.
Mode gating (hard guarantee)
How you act on a detected candidate depends strictly on the session mode, mirroring the audit skill's nit-disposition policy (presence modes ask, autonomous acts on a documented default). The mode comes from the session-mode inject line.
Safe default when the mode is not determinable. A subagent gets no session-mode inject line, so its mode is often unknown. When you cannot determine the mode, apply the SAFEST branch = the autonomous behavior below: append a candidate note only, never ask, never build. This is the same principle by which safety rules always take their strictest reading inside subagents - an unknown mode must never fall through to the ask-and-build branch.
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 · 151 lines · 170 tokens per session scan A 5df02e14deb5
skill-capture is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 170 tokens to every session and 2,031 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
ios-development
Comprehensive guide for building native Apple platform applications.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
battle-card-builder
Competitive battle card creation for sales teams combining competitive intelligence, sales enablement, and document formatting. Use when building battle cards, competitive analysis decks, or win/loss analysis materials.