Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/flonat/flonat-researchnpx agentmods add skills/flonat/flonat-research/skill-extractWrote 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/flonat/flonat-research/skill-extract)<a href="https://agentmods.dev/skills/flonat/flonat-research/skill-extract"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/skill-extract/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/flonat/flonat-research/skill-extract"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/skill-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Anti-Refusal · line 109 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Agent Snooping · line 42 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 | $0.00043 | $0.02202 |
| Opus 5 | $0.00022 | $0.01101 |
| Sonnet 5 | $0.00009 | $0.00440 |
| Haiku 4.5 | $0.00004 | $0.00220 |
Grade A, and why
skill-extract 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 6d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn: Session Knowledge Extraction
Extract reusable workflows, workarounds, and multi-step procedures discovered during a session into persistent skills. Complementary to the learn-tags rule — while [LEARN] tags record one-liner corrections in MEMORY.md, skill-extract creates full skill definitions in skills/.
When to Use
- You discovered a non-obvious multi-step procedure
- You built a workaround for a recurring problem
- You developed a workflow that future sessions would benefit from
- the user says "save this as a skill", "learn this", or "remember how to do this"
Phase 1: Evaluate
Before creating anything, answer these 4 self-assessment questions:
- Non-obvious? Would a future session figure this out without help, or would it waste time rediscovering it?
- Future benefit? Will this come up again across sessions or projects?
- Repeatable? Is this a procedure that can be followed step-by-step, or was it a one-off?
- Multi-step? Does it involve 2+ non-trivial steps that benefit from being documented together?
Decision rule: If at least 3 of 4 answers are "yes", proceed to Phase 2. Otherwise, suggest recording as a [LEARN] tag in MEMORY.md instead (simpler, lower overhead).
If borderline, ask the user:
"This seems useful but may not warrant a full skill. Should I create a skill or just add a [LEARN] tag to MEMORY.md?"
Phase 2: Creation Guard + Read Patterns
Run the skill-preflight analysis (see skills/skill-preflight/SKILL.md):
- Identify the proposal (name, type, purpose, key functions, keywords)
- Search existing skills and agents for overlap (skill-index scan + keyword grep)
- Analyse overlap and generate a recommendation:
| Recommendation | Criteria | Action |
|---|---|---|
| PROCEED | <20% overlap, genuinely new | Continue to Phase 3 |
| EXTEND | 50%+ overlap with one existing | Modify existing skill instead — stop here |
| COMPOSE | Multiple artifacts cover 80%+ | Create wrapper or document workflow — stop here |
| ITERATE | 20-50% overlap, needs refinement | Ask the user to clarify differentiation, then re-evaluate |
| BLOCK | Would create duplication | Do not create — stop here |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 235 lines · 43 tokens per session scan A cf0cf9958714
skill-extract is a skill published in the GitHub repository flonat/flonat-research (132 stars, last pushed 14d ago), licensed MIT. It adds 43 tokens to every session and 2,202 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
done
Wrap up the current session by writing a short HANDOFF.md in the project folder, so the next session can resume quickly. Use when the user says done, wrap up, close this out, or capture the session.
calendar-event-manager
Create macOS Calendar events with tiered sound alarms and paired Reminders so events are never missed across Mac and iOS.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
lark-contact
A Feishu (Lark) contacts tool for finding users or bots and looking up their profiles and contact details.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
ask-agents
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks to ask Claude, ask Gemini, ask both, get a second opinion, split reviewer roles, or compare external agents.