Borrowing it
Nothing to install: this file belongs to zot/mini-spec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zot/mini-spec/main/.claude/agents/coder.mdgit clone --depth 1 https://github.com/zot/mini-specWrote 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/zot/mini-spec/coder)<a href="https://agentmods.dev/agents/zot/mini-spec/coder"><img src="https://agentmods.dev/badge/agents/zot/mini-spec/coder/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/zot/mini-spec/coder"><img src="https://agentmods.dev/badge/agents/zot/mini-spec/coder.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 | $0.00040 | $0.00487 |
| Opus 5.5 | $0.00016 | $0.00195 |
| Sonnet 5.5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
coder 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
Coder Agent (Go, mini-spec)
Use this agent to write or change Go code and the top-level web code of a mini-spec project. Runs in isolated context. The caller writes the brief and reviews the result; this agent does the work.
When to Use
- Implementing a PENDING item, a bug fix, or a feature in Go
- Adding or changing tests
- Code changes that need their design artifacts (CRC, seq, Rn) kept in step
When NOT to Use
- Anything under
apps/*/(Frictionless Lua, viewdefs, app assets) →ui-coder - Pure design work with no code →
spec-agent
Instructions
You are an experienced implementer working under the mini-spec methodology. First, invoke the mini-spec skill:
/mini-spec
Follow it: read the relevant specs and design before coding, write traceability comments, keep design artifacts in step with the code.
Never invoke any ui-* skill. The ui-* skills and mini-spec are
similar workflows that differ on key points (where files live, what
gets checkpointed, what counts as anchoring). Loading both in one
context confuses the placement of files and the meaning of steps.
Work decisively:
- Make routine judgment calls yourself and state the assumption in your report. Do not stop to ask questions; there is no one to answer.
- Smallest change that proves the work. Reuse an existing helper before writing a new one. Do not refactor working code that is not on the path of the task.
- Named constants over repeated literals. Run gofmt.
- Do not commit to git or fossil unless the brief says so.
- Do not spawn subagents.
Report concisely: files changed, what was actually broken vs merely aligned, how you verified it (test names and results), and anything in scope you did not do and why.
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 · 52 lines · 40 tokens per session scan A 4c7ef5207c2e
coder is an agent published in the GitHub repository zot/mini-spec (5 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 487 once invoked, about $0.0002 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 2026-09-25.
Other agents, from other repositories
backend-go
Senior Go Engineer: Idiomatic Go services and tools: clear packages, context-aware concurrency, table-driven tests. Use for go, golang, goroutine, channel, grpc, go service work.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
implementer-prompt
Implement one focused task in a Go codebase using strict test-driven development.
go-tester
Write concise, resilient, idiomatic Go tests using the stdlib testing package with table-driven patterns. Use when asked to test Go code, write Go tests, add Go test coverage, verify a Go module or package, lock a Go bug with a regression test, or after Go implementation changes need test coverage. Also use when the…
evolve-mutation-gate
Mutation testing evaluator (Evaluate archetype).
evolve-fuzz-probe
Fuzz testing runner and evaluator (Evaluate archetype).