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 justfinethanku/LEJ-output-fixer --skill stylegit clone --depth 1 https://github.com/justfinethanku/LEJ-output-fixerWrote 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/justfinethanku/lej-output-fixer/style)<a href="https://agentmods.dev/skills/justfinethanku/lej-output-fixer/style"><img src="https://agentmods.dev/badge/skills/justfinethanku/lej-output-fixer/style/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/justfinethanku/lej-output-fixer/style"><img src="https://agentmods.dev/badge/skills/justfinethanku/lej-output-fixer/style.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 | $0.00049 | $0.01041 |
| Opus 5 | $0.00024 | $0.00521 |
| Sonnet 5 | $0.00010 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade B, and why
style scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **Currently active**: check for an `outputStyle` field in, in order of precedence: `.claude/settings.local.json`, `.claude/settings.json`, `~/.claude/settings.json`. Note which style is active and which file sets it. How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Style Picker
You are helping the user choose or create an output style. Output styles are native Claude Code features — the chosen style replaces the tone/formatting section of the system prompt. Your job: show a menu, apply the choice, confirm.
Step 1 — Gather the options
Build the full list of available styles:
- Bundled with this plugin: Scannable, Bottom Line First, Walk Me Through It.
- Built-in: Explanatory, Learning.
- The user's own: list
*.mdin~/.claude/output-styles/and.claude/output-styles/(if present). Read each file's frontmatter fornameanddescription. Skip files without frontmatter. - Currently active: check for an
outputStylefield in, in order of precedence:.claude/settings.local.json,.claude/settings.json,~/.claude/settings.json. Note which style is active and which file sets it.
Step 2 — Present the menu
Use the AskUserQuestion tool — never make the user type a style name freehand.
- Mark the currently active style in its option description.
- AskUserQuestion allows max 4 options per question. With more choices than fit, lead with the most relevant (bundled presets first, then the user's own) and make the last option "More options…" — if chosen, ask a follow-up question with the rest.
- The menu must always offer a path to two special entries:
- No output style — return to Claude Code's default voice.
- Create new preset — build a custom style (Step 4).
Step 3 — Apply the choice
- A style was chosen: write
"outputStyle": "<reference>"into~/.claude/settings.json(applies everywhere). If the user says they want it only for this project, use.claude/settings.local.jsoninstead. Edit JSON carefully — preserve all existing keys. Usejqor a smallpython3round-trip, never a blind overwrite. - The reference format matters. Styles bundled in a plugin only resolve with the plugin namespace prefix; bare names silently do nothing. Exact values:
- This plugin's styles:
lej-output-fixer:Scannable,lej-output-fixer:Bottom Line First,lej-output-fixer:Walk Me Through It - Built-in and user-created styles: the plain style name (e.g.
Explanatory, or thenamefrom the user's own file)
- This plugin's styles:
- Precedence check: if a more-specific settings file already sets
outputStyle(local overrides project overrides user), tell the user their choice won't take effect until that override is removed, and offer to remove it. - No output style: remove the
outputStylekey from whichever settings file(s) set it. Confirm with the user before touching a project-level file they may share with a team. - Confirm: state what's now active and which file controls it. Note that if the change doesn't take effect immediately, starting a new session will pick it up.
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 · 72 lines · 49 tokens per session scan B 068cff7cc3d3
style is a skill published in the GitHub repository justfinethanku/LEJ-output-fixer (11 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,041 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
review
Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.
skill-monitor
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
promote
Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.