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 commands/blencorp/claude-code-kit/build-and-fixgit clone --depth 1 https://github.com/blencorp/claude-code-kitWhat 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 | $0.00011 | $0.00579 |
| Opus 5 | $0.00005 | $0.00290 |
| Sonnet 5 | $0.00002 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade B, and why
build-and-fix scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!cat "$CLAUDE_PROJECT_DIR/.claude/tsc-cache"/*/affected-repos.txt 2>/dev/null | sort -u || echo "No services modified yet" How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a build engineer focused on ensuring zero compilation errors and a clean build state.
Philosophy: #NoMessLeftBehind
We NEVER leave broken builds. Every change must compile cleanly.
Context
Services modified this session (auto-generated):
!cat "$CLAUDE_PROJECT_DIR/.claude/tsc-cache"/*/affected-repos.txt 2>/dev/null | sort -u || echo "No services modified yet"
User-specified services: $ARGUMENTS
Your Task
Build the project and fix all errors:
-
Detect Build System
- Check for TypeScript (tsconfig.json)
- Check for build scripts in package.json
- Identify monorepo structure if present
-
Run Builds
- For each service/package that was modified:
- Run TypeScript compilation (
tsc --noEmitor equivalent) - Run build script if defined (
npm run buildor similar) - Capture all errors and warnings
- Run TypeScript compilation (
- For each service/package that was modified:
-
Fix Errors Automatically
- Use the Task tool to launch the auto-error-resolver agent with:
- subagent_type:
auto-error-resolver - description:
fix build errors - prompt: List all services with build errors and ask the agent to:
- Run the builds and analyze errors
- Fix errors systematically
- Verify each fix by re-running the build
- Continue until achieving zero errors
- subagent_type:
- Use the Task tool to launch the auto-error-resolver agent with:
-
Verify Clean Build
- Re-run builds after fixes
- Ensure zero errors and zero warnings
- Report final build status
Build Commands by Project Type
Frontend (React/Vite):
npm run build
# or
npx tsc --noEmit
Backend (Node.js/Express):
npx tsc --noEmit
# or for specific tsconfig
npx tsc --project tsconfig.build.json --noEmit
Monorepo:
# Build specific service
cd services/[service-name]
npm run build
Quality Standards
- Must achieve zero compilation errors
- Must achieve zero build errors
- Report all warnings even if they don't fail the build
- Provide clear summary of what was fixed
- Include build time and success confirmation
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.
- 3d ago First seen · 98 lines · 11 tokens per session scan B 9e6ec568f551
build-and-fix is a command published in the GitHub repository blencorp/claude-code-kit (101 stars, last pushed 9mo ago), licensed MIT. It adds 11 tokens to every session and 579 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.