Borrowing it
Nothing to install: this file belongs to ymm-oss/fsl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ymm-oss/fsl/main/.agents/skills/focused-change/SKILL.mdgit clone --depth 1 https://github.com/ymm-oss/fslWrote 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/ymm-oss/fsl/focused-change)<a href="https://agentmods.dev/skills/ymm-oss/fsl/focused-change"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/focused-change/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/ymm-oss/fsl/focused-change"><img src="https://agentmods.dev/badge/skills/ymm-oss/fsl/focused-change.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00679 |
| Opus 5.5 | $0.00019 | $0.00272 |
| Sonnet 5.5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
focused-change 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focused change workflow
Input contract
Extract and keep visible only:
- Goal
- Target paths or symbols
- Constraints and non-goals
- Observable acceptance conditions
- Required checks
When one of these is missing, infer at most three low-risk assumptions from repository evidence. Do not expand the task to “improve the surrounding code.”
FSL repository routing
In the FSL repository, read
references/fsl-repository-contract.md
completely before changing implementation, tests, verification, language
semantics, conformance, CLI/Worker/Kernel contracts, generated snapshots,
soundness evidence, CI/product gates, or release surfaces. The reference
preserves detailed repository obligations that are intentionally omitted from
the short root AGENTS.md.
For a small prose-only correction that cannot affect a contract or executable
surface, the root AGENTS.md is sufficient.
Discovery funnel
- Run
git status --short. - Search named symbols, error strings, tests, or routes with
rg -n. - Read only the relevant ranges and immediately adjacent contracts.
- Identify the shortest test or reproducer before changing code.
- Widen to callers/dependencies only when the current evidence cannot explain behavior.
Stop discovery when there is enough evidence to describe:
- the current behavior,
- the intended behavior,
- the smallest likely change,
- how the change will be falsified.
Plan
For a small task, give a plan of at most four steps. For a trivial mechanical task, proceed without a separate plan. Do not create a long planning document unless requested.
Implementation
- Make the smallest coherent edit.
- Follow an existing local pattern before inventing an abstraction.
- Avoid new dependencies unless acceptance requires them.
- Do not rewrite unaffected code.
- Add or update a test when it is the clearest executable expression of the changed contract.
Command-output control
For noisy commands, use:
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 · 100 lines · 48 tokens per session scan A 7b58ed8c6761
focused-change is a skill published in the GitHub repository ymm-oss/fsl (35 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 679 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
wrap-up
Use ONLY when the user's latest message explicitly contains the /wrap-up command. Harvests everything a long session produced into the project following that project's own rules — moves stray media in, wires two-way refs, updates indexes, merges drafts into SSOT — then dispatches a context-free sub-agent to blind-test…
skill-cron
Use when the user wants to register, inspect, manually run, or remove scheduled Claude skills with Telegram push notifications. Presents a menu, discovers schedulable skills with headless-prompt frontmatter, converts natural-language schedules into cron entries with conflict confirmation, writes managed config, and…
kalender
Calendar skill with user-adaptive backend selection (Flag 3). Default: local SQLite store. Optional: Google Calendar MCP, Routinika or UpToday as backend — controlled via assist/prefs.json. Without preference the LLM asks the user interactively.
bewerbungsexperte
Spezialist fuer den gesamten Bewerbungsprozess. Analysiert Stellenanzeigen, optimiert Profile (LinkedIn/CV) und generiert massgeschneiderte Anschreiben. Generiert ASCII-Lebenslaeufe aus einer SQLite-Datenbank und Ordnerstruktur. cvgenerator.py ist standalone portiert -- keine BACH-Runtime noetig.