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 bgill55/daedalus --skill fix-typescript-buildgit clone --depth 1 https://github.com/bgill55/daedalusWrote 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/bgill55/daedalus/fix-typescript-build)<a href="https://agentmods.dev/skills/bgill55/daedalus/fix-typescript-build"><img src="https://agentmods.dev/badge/skills/bgill55/daedalus/fix-typescript-build/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/bgill55/daedalus/fix-typescript-build"><img src="https://agentmods.dev/badge/skills/bgill55/daedalus/fix-typescript-build.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 | $0.00038 | $0.00838 |
| Opus 5.5 | $0.00015 | $0.00335 |
| Sonnet 5.5 | $0.00008 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
fix-typescript-build 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixing a TypeScript Build (npm run build / tsc)
The project's build script is usually tsc --noEmit (a type-check, not a bundle).
A failing build means type errors. Fix them deliberately — do NOT blast the whole
codebase in one giant turn (that burns the context window and makes review impossible).
Prefer
npm run buildovernpx tsc.npx tscis not a declared dependency in most projects, sonpxwill try to download thetscpackage from the registry — that download is slow and flaky (and can be killed by the terminal's process-group isolation on Windows).npm run builduses the project's local TypeScript.
Process
- Get the full error list first. Run
npm run build(the project'sbuildscript). Only fall back tonpx tsc --noEmitif the project has nobuildscript. Capture EVERY error line. Do not guess — read the actual compiler output. - Group errors by file. Most real projects concentrate errors in a few files. Present the grouped summary to the user and STOP to confirm scope before editing (audit/review etiquette: list findings, then ask which to fix).
- Once confirmed, FIX FILE-SCOPED. For each target file:
- Read the file, make the minimal change (rename an unused param to
_x, switchobj.keytoobj['key']when the type is an index signature, etc.). - The syntax checker will NOT false-revert a valid edit just because the file already had other errors — it diffs pre- vs post-edit diagnostics. So fix one file at a time confidently; a valid edit won't be blamed for pre-existing errors.
- Read the file, make the minimal change (rename an unused param to
- Re-run
npm run buildafter each file (or each small batch) to confirm the errors for that file are gone. Iterate until the build is clean. - Run the test suite (
npm test) to confirm nothing broke. Report the final state.
Context-window discipline (important)
- Break the work into SPRINTS: e.g. Sprint 1 = fix
validation.ts, Sprint 2 = fixserver.ts. After each sprint, the build gets greener and you checkpoint. - Keep each turn's edits SMALL (one file, few lines). Do NOT dump a 100-line rewrite of a file that only needed 3 lines changed — that is what burns context and trips the patch tooling.
- Use the
todotool to track sprints so progress survives across turns.
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 · 57 lines · 38 tokens per session scan A e37088f7341e
fix-typescript-build is a skill published in the GitHub repository bgill55/daedalus (4 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 838 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
angular
Use when building, refactoring, or debugging Angular (v20/21+): standalone components, signals, zoneless change detection, @if/@for/@defer control flow, inject() DI, resource()/httpResource(), RxJS interop, NgRx SignalStore, ng CLI. NOT React (that is react), NOT Next.js (that is nextjs), NOT a TypeScript language…
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
async-await-patterns
Use when writing JavaScript or TypeScript code with asynchronous operations, fixing promise-related bugs, or converting callback/promise patterns to async/await. Triggers: 'promise chain', 'unhandled rejection', 'race condition in JS', 'callback hell', 'Promise.all', 'sequential vs parallel async', 'missing await'.…
javascript-sandbox
Best practices for using the clodex built-in JavaScript sandbox for browser debugging, fetched-data processing, attachments, and mini-app orchestration within its bundled capability boundary.
ts-debug
TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".
strict-typescript
Enforce strict TypeScript compiler settings and type narrowing patterns. Use when the user creates a new TypeScript project, configures tsconfig.json, encounters null/undefined errors, deals with indexed access issues, or asks about strict mode, type safety, or narrowing techniques.