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.
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWrote 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/agents/mckruz/claude-code-sdlc/build-error-resolver)<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/build-error-resolver"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/build-error-resolver/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/agents/mckruz/claude-code-sdlc/build-error-resolver"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/build-error-resolver.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 | $0.00072 | $0.00431 |
| Opus 5.5 | $0.00029 | $0.00172 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (8 stars, last pushed 10d ago), licensed MIT. It adds 72 tokens to every session and 431 once invoked, about $0.0003 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.