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 ankitkr3/compounded --skill compounded-typo-fixergit clone --depth 1 https://github.com/ankitkr3/compoundedWrote 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/ankitkr3/compounded/compounded-typo-fixer)<a href="https://agentmods.dev/skills/ankitkr3/compounded/compounded-typo-fixer"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/compounded-typo-fixer/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/ankitkr3/compounded/compounded-typo-fixer"><img src="https://agentmods.dev/badge/skills/ankitkr3/compounded/compounded-typo-fixer.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 | $0.00059 | $0.00798 |
| Opus 5.5 | $0.00024 | $0.00319 |
| Sonnet 5.5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
compounded-typo-fixer 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typo Fixer
A demo skill that ships with compounded to show the full lifecycle. Starts as .verified (we shipped it pre-verified to make the demo work). After 3 successful uses without correction, it auto-promotes to .trusted. After 10 uses with zero corrections in the last 5, it goes .autonomous.
When to use
- The user reports a misspelling and asks for it to be fixed everywhere
- You notice a misspelled identifier in a code review and decide it should be corrected
- The user provides both the wrong spelling and the correct one explicitly
Inputs
<wrong>: the misspelled token (case-sensitive by default)<right>: the correct token<scope>(optional): a directory to limit the search to. Default: the project root.
Procedure
-
Confirm with the user: "Replacing
<wrong>with<right>" — show this before searching. -
Run a recursive search for the wrong spelling:
grep -rn "<wrong>" <scope> --include="*.{ts,tsx,js,jsx,py,go,rs,md,txt}" 2>/dev/nullAdjust the
--includeglob to match the project's primary languages. -
Review the matches. For each one, decide if it is a true positive (a real instance of the typo) or a false positive (a substring that incidentally contains the typo, or a deliberate use like in a test fixture).
-
If any false positives exist, list them to the user and ask which to skip.
-
Apply the replacements via the
Edittool, one file at a time. Do NOT usesed -ifor this — it is too easy to corrupt files when the replacement is not what was expected. -
After all edits, re-run the grep to verify no instances of
<wrong>remain in the affected files. -
Run the project's test suite if one exists, to verify nothing broke. Common commands:
npm test,pytest,cargo test,go test ./....
Pitfalls
- Substring false positives.
recieveis a typo.recieve_countcontainingrecieveis also a typo and should be fixed. Butreceived(correct) containsrecei, and a careless replacement ofrecei→reciewould corrupt it. Always match whole tokens when possible.
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 · 63 lines · 59 tokens per session scan A b25443e473a3
compounded-typo-fixer is a skill published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 798 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 2026-08-31.
Other skills, from other repositories
broken-links
Find and fix broken links — three modes with different scale ceilings. local audits any local repo (HTML/MD/MDX, no size limit) via Glob/Grep + per-link verification. page checks one live URL deeply (30-100 outbound links per run). site requires the Ahrefs site-audit MCP for true multi-page crawl — without it, refuses…
vigil-instrument
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
forge-diagnose
Diagnose runtime infrastructure issues — cold starts, timeouts, scaling problems, network failures. Use when asked about "infra is slow", "cold starts", "network issues", "why is this timing out", "scaling problem", "latency spikes", or "service is down".
spine-recon
Backend reconnaissance — map all routes, middleware, models, dependencies, auth, and assess code quality for project takeover. Use when asked to "understand this backend", "map the API", or "assess code quality".
analyze
Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…