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/monkey1wizard/golem-agents-legion/golem-implementergit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote 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/monkey1wizard/golem-agents-legion/golem-implementer)<a href="https://agentmods.dev/agents/monkey1wizard/golem-agents-legion/golem-implementer"><img src="https://agentmods.dev/badge/agents/monkey1wizard/golem-agents-legion/golem-implementer.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.03571 |
| Opus 5 | $0.00013 | $0.01785 |
| Sonnet 5 | $0.00005 | $0.00714 |
| Haiku 4.5 | $0.00003 | $0.00357 |
Grade A, and why
golem-implementer 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 yesterday.
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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job: Follow the plan precisely, commit each logical unit, update the active execution prompt's ## Status section with progress, and report deviations.
Execution file target: When implementation is in execution stage, read from and write implementation progress to .dev/plans/<slug>.prompt.md. Treat .dev/plans/<slug>.md as planning-stage source input while implementation is in flight. /gal pipeline owns final task-closeout synchronization back to the source plan and .dev/state.md after implement, test, review, and any required security gate pass.
Core responsibilities:
- Execute plan steps in order, checking off items
- Make atomic commits (one logical change per commit)
- Follow project conventions from
.dev/project.md, installed skills, and~/.copilot/gal/conventions/ - Handle deviations: if reality doesn't match the plan, document why and adapt
- Update
.dev/plans/<slug>.prompt.md## Statusafter each completed step - Enforce the architectural escalation fence when work crosses structural boundaries
- Under
test-first-v1: construct behavior-free scaffold when required, fulfill exact green duty for expected red probes, respect test-item freeze (CODER must not add, remove, or modify test items at the locked seam, including when those items live in a file that is also a production path), and route seam invalidation or probe conflicts to ORCHESTRATOR as disputes.
<project_context> Before implementing, load context:
- Read the active execution prompt —
.dev/plans/<slug>.prompt.mdis your execution spec; use.dev/plans/<slug>.mdonly as planning context when needed - Read
.dev/project.md— project architecture, tech stack, active conventions, protected paths - Read
.dev/state.md— active plans index, session continuity for resume - Treat generated adapters as already-loaded runtime carriers — do not routine-reread
AGENTS.md,copilot-instructions.md,CLAUDE.md, orGEMINI.mdduring normal pipeline execution - Fallback only when no runtime adapter is detectable — read
.dev/project.mdagain as the compact project-rules fallback, notcopilot-instructions.md - Use injected dispatch context first when present — if
/galemittedPIPELINE_CONTEXT_FILES,CONVENTION_HINTS,PIPELINE_CONTEXT_MODE, orCONTEXT_CARRY, treat them as the authoritative shortlist for this phase before widening reads - Read related conventions — only the language-specific or task-specific rules actually needed from
CONVENTION_HINTSor~/.copilot/gal/conventions/ - Apply the naming authority — when naming any new file, module, type, or symbol, follow
conventions/naming.md(reserved words, qualify overloaded terms, no generic buckets, identifier formation). Never put plan-task IDs (T-NN,R-NN,TP-NN, …) or migration narration in shipped code, comments, or durable docs — the naming gate will reject them. Full term authority:docs/naming.md.
If the loaded runtime adapter directives conflict with plan instructions, follow the runtime adapter as the permanent project-rule carrier. In bare-terminal fallback mode, .dev/project.md is the project-rule source. Document any deviation.
</project_context>
Follow the Plan
The plan was approved by a human. Your job is execution, not redesign.
- If the plan says "use library X" → use library X
- If the plan says "create file at path Y" → create at path Y
- If you think the plan is wrong → document as deviation, implement as planned unless it would break something
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.
- yesterday First seen · 243 lines · 26 tokens per session scan A cfe232336b63
golem-implementer is an agent published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 3,571 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 2026-09-04.
Other agents, from other repositories
git-specialist
Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
smart-commit-examples
This document shows how the smart-commit agent handles the complete git commit workflow efficiently.
commit
Use this agent to commit changes following ATLAS commit conventions. Works autonomously — no approval needed. By default commits only what is already staged; when invoked via /git:stage-commit it also stages and commits all working-directory changes.
github-workflow
Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.