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 IgorGanapolsky/ThumbGate --skill prevention-rulesgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/prevention-rules)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/prevention-rules"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/prevention-rules/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/igorganapolsky/thumbgate/prevention-rules"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/prevention-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00216 |
| Opus 5 | $0.00009 | $0.00108 |
| Sonnet 5 | $0.00004 | $0.00043 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
prevention-rules 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 10d 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
Prevention Rules
Manage prevention rules that are auto-generated from repeated failure patterns.
When to use
- Reviewing current active prevention rules for the project
- Checking if a specific action is blocked by a prevention rule
- Understanding why an action was blocked
- Generating new prevention rules from observed patterns
How it works
Use the prevention_rules MCP tool to:
- List rules — View all active prevention rules with their match patterns and corrective actions.
- Check rules — Test if a specific action matches any prevention rule before execution.
- Review rule history — See which feedback events led to a rule's promotion.
Example
Check prevention rules for "npm publish without running tests" to see if this action is blocked.
Prevention rules are auto-promoted when the same failure pattern appears multiple times in captured feedback. Each rule includes the original failure context and a corrective action.
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.
- 10d ago First seen · 32 lines · 18 tokens per session scan A bf349c26fe13
prevention-rules is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 216 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 2026-08-30.
Other skills, from other repositories
learning-from-experience
Turns incidents, near misses, bad handoffs, review surprises, escaped bugs, and signals from real use into lasting fixes to your safeguards. Use after something went wrong or nearly did and a future safeguard should change. Do not use during a live incident, which comes first, or to blame someone.
reporting-shared-defects
Routes a defect found in a shared or supplied artifact (a shared prompt, skill, dependency, model, eval, or template) to the downstream teams, agents, and releases that depend on it, not just a local fix. Use when a discovered defect affects others who consume the same artifact. Do not use for a defect local to your…
responding-to-incidents
Runs a live incident the stabilize-first way — name a commander, separate facts from hypotheses, prefer reversible actions, communicate on a cadence, and drive corrective actions to closure. Use when production is broken, data is at risk, or an agent action caused harm. Do not use for routine non-incident work, or as…
bug-fix
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.
forge-troubleshoot
Diagnose and resolve Plan Forge issues — failed runs, broken validation gates, misconfigured environments, stalled slices, and orchestrator errors. Use when a plan run fails or the forge behaves unexpectedly.
audit-loop
Run a recursive audit drain loop — discover findings from the running system, triage each into bug/spec/classifier lanes, repeat until convergence. USE FOR: end-to-end audit of a deployed or locally-running app, draining findings to zero. DO NOT USE FOR: single-shot tempering runs (use forgetemperingrun), one-off bug…