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 richfrem/agent-plugins-skills --skill synthesize-learningsgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/synthesize-learnings)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/synthesize-learnings"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/synthesize-learnings/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/richfrem/agent-plugins-skills/synthesize-learnings"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/synthesize-learnings.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 | $0.00066 | $0.01604 |
| Opus 5 | $0.00033 | $0.00802 |
| Sonnet 5 | $0.00013 | $0.00321 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
synthesize-learnings 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ./requirements.txt for the dependency lockfile (currently empty — standard library only).
Synthesize Learnings
Take raw analysis output from analyze-plugin and transform it into concrete, actionable improvements for our meta-skills ecosystem. This is the "close the loop" skill that turns observations into evolution.
Improvement Targets
Learnings are mapped to three improvement targets:
Target 1: agent-scaffolders
Improvements to the plugin/skill/hook/sub-agent scaffolding tools.
What to look for:
- New component types or patterns that
scaffold.pyshould support - Better default templates based on exemplary plugins
- New scaffolder skills needed (e.g., creating connectors, reference files)
- Improved acceptance criteria templates based on real-world examples
Target 2: agent-scaffolders
Improvements to ecosystem standards and authoritative source documentation.
What to look for:
- New best practices discovered from high-quality plugins
- Anti-patterns that should be documented as warnings
- Spec gaps where plugins do things the standards don't address
- New pattern categories to add to ecosystem knowledge
Target 3: agent-scaffolders (Self-Improvement)
Improvements to this analyzer plugin itself.
What to look for:
- New patterns discovered that should be added to
pattern-catalog.md - Analysis blind spots — things that should have been caught
- Framework gaps — phases that need refinement
- New anti-patterns to add to the detection checklist
Target 4: Domain Plugins (e.g., oracle-legacy-system-analysis)
Improvements to the primary domain plugins in this repository — especially the legacy Oracle Forms/DB analysis plugins.
What to look for:
- Severity/classification frameworks that could improve how legacy code issues are categorized (e.g., GREEN/YELLOW/RED deviation severity from legal contract-review)
- Playbook-based review methodology adaptable to legacy code review playbooks (standard migration positions, acceptable risk levels)
- Confidence scoring applicable to legacy code analysis certainty levels
- Connector abstractions (
~~categorypatterns) for tool-agnostic Oracle analysis workflows - Progressive disclosure structures for organizing deep Oracle Forms/DB reference knowledge
- Decision tables for legacy migration pathways (like chart selection guides but for migration strategies)
- Checklist patterns for legacy system audit completeness
- Tiered execution strategies for handling different legacy code complexity levels
- Bootstrap/iteration modes for incremental legacy system analysis
- Output templates (HTML artifacts, structured reports) for presenting legacy analysis results
What ships with it
11 files 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.
- acceptance-criteria.md 1.1 KB
- evals/evals.json 657 B
- evals/results.tsv 301 B
- fallback-tree.md 1.5 KB
- pattern-catalog.md 35 B
- references/acceptance-criteria.md 42 B
- references/fallback-tree.md 36 B
- references/improvement-mapping.md 42 B
- references/input-contract.md 37 B
- references/open-recommendations.md 43 B
- requirements.txt 22 B
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 · 172 lines · 66 tokens per session scan A 31bfb42a859c
synthesize-learnings is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 1,604 once invoked, about $0.0003 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
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
close-issue
Close a GitHub or GitLab issue with a summary comment.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
bbc-skill
A read-only tool for collecting all comments from a Bilibili video, including replies and pinned comments. Bilibili is a Chinese video-sharing platform.
feature-implementation
Implement software features, fix bugs, and write production-quality code. Use this for hands-on development work including writing new code, modifying existing code, and debugging issues.