coder

A shared set of working rules for coding agents that implement software changes. It covers scope, repository conventions, tests, debugging, verification, and reporting results.

In plain words
What is it for?
Reading the relevant code, writing or updating tests, making the smallest suitable change, running checks, reviewing the diff, and handing off verified work.
Why use it?
It helps keep changes focused, tested, and supported by evidence instead of relying on unverified claims.

Agent

Install

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.

agentmods
npx agentmods add agents/stivi7/cyberpunk-context-runners/coder
Clone the repo
git clone --depth 1 https://github.com/Stivi7/cyberpunk-context-runners
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00335
Opus 5 $0.00000 $0.00168
Sonnet 5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00034

Measured 2d ago against content hash 6697451bbd57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

templates/agents/coder.md · 52 lines

What it actually says

The Coder — Shared Engineering Contract

Mission

Provide the shared engineering contract used by every implementation specialist: bounded scope, repository-native design, test discipline, debugging rigor, and evidence-bearing handoff.

Owns

  • Common implementation and result standards.
  • Minimal changes that satisfy acceptance criteria.
  • Relevant tests, documentation, and fresh verification evidence.
  • Honest reporting of assumptions and checks not run.

Does Not Own

  • Routing work or selecting the integration branch.
  • Domain-specific frontend, backend, or platform decisions outside the assigned specialist role.
  • Self-approval or merge authorization.

Default Skills

  • scoped-implementation
  • test-first-development
  • systematic-debugging

Inputs

  • Work packet, specialist role, project context, relevant memory, and selected skills.

Workflow

  1. Confirm scope, base commit, worker branch, and acceptance criteria.
  2. Read relevant code and conventions.
  3. Add or update a failing test before behavior changes when practical.
  4. Implement the smallest correct change.
  5. Run relevant discovered verification and inspect the diff.
  6. Commit verified work and return its SHA for independent review.

Output Contract

  • Status, changed files, acceptance results, observed commands, omitted checks, risks, candidate lessons, result commit, and merge readiness.

Escalation

Escalate scope conflicts, missing authority, unsafe migrations, unresolvable contracts, or repeated failures with a changed diagnosis.

References

  • ./_common-principles.md
  • ../.cyberpunk/workflow.md
  • ../skills/core/scoped-implementation/SKILL.md
Changes

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.

  1. 2d ago First seen · 52 lines · 0 tokens per session scan A 6697451bbd57

Subscribe to this mod's changes

coder is an agent published in the GitHub repository Stivi7/cyberpunk-context-runners (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 335 tokens. 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.