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 agentmods add skills/fledgeling-co/fledgeling-plugins/improve-skillnpx skills add fledgeling-co/fledgeling-plugins --skill improve-skillgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/improve-skill)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/improve-skill"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/improve-skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00226 | $0.02502 |
| Opus 5 | $0.00113 | $0.01251 |
| Sonnet 5 | $0.00045 | $0.00500 |
| Haiku 4.5 | $0.00023 | $0.00250 |
Grade A, and why
improve-skill 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 5d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
improve-skill
Take a skill that exists, learn everything about why it is the way it is, research what the world has learned since it was written, rebuild it better, and prove the rebuild — with evals the original is scored on too, and blind judges who don't know which output came from which version. Then ship it like a product: named by the user, iconed through the full design pipeline, documented for a non-technical reader, pushed.
The pipeline is long. Its honesty rules are what make it worth running: research is read in full and citation-verified, judges never see the skill or know which take is which, losing takes stay on the audit sheet, and a finding becomes a rule in the skill the same day it's confirmed.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Turns this pipeline's stated standards into steps with outputs: filled quota and bound ledgers, a receipt check on the phases that own no exit code, and the banner's two skills chained through files a later step reads. Other models skip it.
Phase 0 — Intake
Gather three things before anything runs:
- The source. The skill's repo/directory, its SKILL.md, references, evals, benchmarks, README. Read all of it. If the source repo is third-party (origin not owned by the user), it is read-only evidence — the improved skill is born in this marketplace, and the original gets a genuine, named shoutout in the README, never silent appropriation.
- The feedback. What the user has seen go wrong, plus whatever the source's own eval history records (a benchmark loss is the most valuable input you'll get — it names the exact failure to engineer away).
- A working name. The final name comes later, from the user; use the source's name with a suffix until then.
Phase 1 — Research (starts first, runs in background)
Kick off the Dossier deep-research panel immediately — it runs 5–60
minutes and everything else can proceed while it does. Protocol,
budget rules, and the read-in-full requirement: references/research.md.
What ships with it
5 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.
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.
- 5d ago First seen · 191 lines · 226 tokens per session scan A c1486157b655
improve-skill is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 226 tokens to every session and 2,502 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…