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/drvoss/everything-copilot-cli/build-error-resolvergit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWhat 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 | $0.00019 | $0.01550 |
| Opus 5 | $0.00010 | $0.00775 |
| Sonnet 5 | $0.00004 | $0.00310 |
| Haiku 4.5 | $0.00002 | $0.00155 |
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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Error Resolver Agent
Purpose
The Build Error Resolver agent takes build, compilation, or type-checking output that contains errors and systematically resolves them. It parses error messages, identifies root causes, applies targeted fixes, and verifies the build succeeds.
This is a fast, focused agent that uses the task agent type for efficient
command execution with minimal output on success and full diagnostics on failure.
When to Use
- A build command fails (
npm run build,tsc,go build,cargo build,dotnet build) - TypeScript/ESLint/Pyright reports type errors
- CI/CD pipeline fails with compilation errors
- After a dependency update breaks types or imports
- After a large refactor introduces broken references
- When the user pastes error output and asks to "fix this"
How It Works
- Capture errors – Run the build command and collect the full error output.
- Parse – Extract structured information from each error:
- File path and line number
- Error code (e.g., TS2345, E0308, CS1061)
- Error message
- Related/caused-by chain
- Categorize – Group errors by root cause. Many errors cascade from a single issue. Fix root causes first.
- Fix – Apply the minimal, surgical fix for each root cause:
- Missing imports → add the import
- Type mismatches → correct the type or add proper conversion
- Missing properties → add required fields
- Deleted references → update to new API or remove usage
- Verify – Re-run the build to confirm all errors are resolved and no new ones appeared.
- Iterate – If new errors appear after fixing, repeat the cycle.
Copilot CLI Integration
- agent_type:
task– optimized for command execution. Returns brief summaries on success ("Build succeeded, 0 errors") and full output on failure (stack traces, compiler errors). - Model: Uses
gpt-5-minifor fast, cost-effective error resolution. Most build errors don't need premium reasoning. - Iteration: The agent runs build → fix → build → fix cycles until clean or a maximum iteration count is reached.
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 · 186 lines · 19 tokens per session scan A d530ce7a7026
build-error-resolver is an agent published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 1,550 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
compactor
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
architect
Design specialist for planning features and changes. Use PROACTIVELY at the start of non-trivial tasks before any implementation begins.
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
product-mgr
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
player
Directly pilot, review, and improve Slay the Spire 2 runs like a persistent human player.