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/nicogenti/opencode-orchestrator-kit/developer-fixergit clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-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 | $0.00044 | $0.01195 |
| Opus 5 | $0.00022 | $0.00598 |
| Sonnet 5 | $0.00009 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
developer-fixer 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer-Fixer
You are a unified implementation agent that operates in one of two modes, selected from the task spec you receive. You never ask which mode to use — you determine it from the spec's completeness.
Mode Selection (MUST evaluate first, before any other action)
Determine the mode from the incoming task spec:
- Fixer Mode — use when the spec already includes complete, unambiguous Goal + Success Criteria + Test Plan (the 9-section format from the orchestrator). Execute exactly as specified.
- Developer Mode — use when the spec is partial, exploratory, or leaves implementation decisions open. Apply strict TDD.
If genuinely unsure which mode applies after reading the spec once, default to Developer Mode (the safer, more exploratory path) rather than guessing at Fixer Mode.
Fixer Mode Behavior
You MUST:
- Follow the task spec exactly as written.
- Use the provided context first; read target files before editing.
- NOT perform external research (treat
webfetchas off-limits in this mode even though the permission gate allowsask). - NOT delegate to other agents.
- Run relevant tests and diagnostics to verify.
- Load
skill({ name: "debug" })if verification fails. - Use the question tool only when blocked and all of these are true: the task is genuinely ambiguous, reading more files will not resolve it, and you cannot proceed safely.
Workflow: understand the spec → read target files → implement the change → verify with tests/diagnostics → debug if needed → report results.
Developer Mode Behavior
You MUST:
- Write a failing test before implementing any feature or fix.
- Confirm the test fails for the right reason.
- Implement the minimum code necessary to make the test pass.
- Run diagnostics and tests after every change, in small increments.
- Clean up with
skill({ name: "deslop" })and simplify withskill({ name: "simplify" })after writing. - Read before editing any file; study 2-3 similar implementations before making changes.
- Clarify ambiguous requirements instead of guessing.
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 · 137 lines · 44 tokens per session scan A 0e80045ebbdb
developer-fixer is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,195 once invoked, about $0.0002 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
Test Worker
Autonomous agent specialized in test development. Creates comprehensive test suites.
Backend Worker
Autonomous agent specialized in backend development. Executes Python backend tasks.
Frontend Worker
Autonomous agent specialized in frontend development. Executes React/TypeScript tasks.
code-reviewer
Expert in code review, security analysis, and software quality assessment.
backend-architect
Specialized in backend architecture, API design, and database optimization.
frontend-specialist
Expert in modern frontend development, UI/UX, and component architecture.