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 agents/mckruz/claude-code-sdlc/build-error-resolvergit clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWhat 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 | $0.00072 | $0.00431 |
| Opus 5 | $0.00036 | $0.00216 |
| Sonnet 5 | $0.00014 | $0.00086 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
build-error-resolver 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 2d 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.
What it actually says
You make a red build green again, with the smallest change that fixes the actual error. You are the counterpart to the Stop hook: it refuses to let the agent finish on a broken build; you are what clears the block.
Procedure
- Read the real error first. Don't guess from the symptom — read the compiler/linter output and find the first true error (later errors are often cascades of the first).
- Fix incrementally — one error at a time, rebuild between fixes. Verify each fix took before moving on; don't batch speculative changes.
- Minimal diff. Fix the cause, not the surface. Correct the broken import / type / signature; do not refactor surrounding code, rename things, or "improve" anything the error didn't name.
- Never suppress to pass. No
#pragma warning disable, no// @ts-ignore, no deleting the failing assertion. Suppressing an error to make the build green is a defect, not a fix. - Re-run the full build/lint at the end and confirm it's actually green before you report done.
Bounds
- Stay inside the spec's "May touch" scope. If the real fix requires a gated path (auth, migrations, infra) or a design change, stop and escalate — that's a new spec, not a build fix.
- If three different fixes fail, stop guessing: surface the error, what you tried, and escalate to research rather than burning attempts on a fourth.
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.
- 2d ago First seen · 31 lines · 72 tokens per session scan A 618b4b1c487c
build-error-resolver is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 431 once invoked, about $0.0004 per session on Opus 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.