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 amp-skillgit 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/amp-skill)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/amp-skill"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/amp-skill/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/amp-skill"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/amp-skill.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 MCP Rug Pull · line 21 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 45 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00025 | $0.00526 |
| Opus 5.5 | $0.00010 | $0.00210 |
| Sonnet 5.5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
thumbgate-feedback 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 1mo 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
ThumbGate Feedback Skill (Dual-Write)
This skill captures feedback in TWO places simultaneously:
- Amp MCP memory — for immediate in-session recall (native to Amp)
- thumbgate — for DPO export, LanceDB vectors, prevention rules, and cross-platform analytics
On thumbs up / positive feedback
First, store in Amp's native memory for in-session recall:
Use mcp__memory__remember to store: "GOOD: {context}. What worked: {details}"
Then, pipe to thumbgate for DPO export and analytics:
npx -y thumbgate capture --feedback=up --context="..." --what-worked="..." --tags="..."
On thumbs down / negative feedback
First, store in Amp's native memory so the mistake is recalled immediately:
Use mcp__memory__remember to store: "BAD: {context}. What went wrong: {details}. Fix: {what to change}"
Then, pipe to thumbgate for prevention rules and DPO pairs:
npx -y thumbgate capture --feedback=down --context="..." --what-went-wrong="..." --what-to-change="..." --tags="..."
Before starting a new task
Recall from Amp's memory (instant, in-session):
Use mcp__memory__recall with query describing the current task
Also check thumbgate for cross-session prevention rules:
npx -y thumbgate rules
Triggers
- "thumbs up" / "that worked" / "looks good" / "nice" / "perfect"
- "thumbs down" / "that failed" / "that was wrong" / "no" / "fix this"
Negative Triggers (do NOT activate for)
- "generate code" / "search files" / "explain this" / "run tests"
Why dual-write?
Amp's MCP memory gives you instant in-session recall. thumbgate gives you:
- DPO training pairs for fine-tuning your model
- Prevention rules that block repeated mistakes
- Cross-platform portability — same feedback works in Claude, Codex, Gemini
- LanceDB vector search for semantic similarity across sessions
- REST API for team dashboards and analytics
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.
- 1mo ago First seen · 65 lines · 25 tokens per session scan A 2293c0fa8073
thumbgate-feedback is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (29 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 526 once invoked, about $0.0001 per session on Opus 5.5. 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
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
cordis-plugin-sofagent-evolve
A sofagent add-on for recording lessons from completed work and refining future agent instructions.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
persist
Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when saving project decisions, recording patterns, or updating long-term memory.
recall
Retrieve prior decisions, rationale, and learned patterns from memory to apply consistently. Use when needing context from previous interactions, looking up past decisions, or ensuring consistency with prior reasoning.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.