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.
git clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWrote 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/pablomarin/claude-codex-forge/forge-v6-producer)<a href="https://agentmods.dev/agents/pablomarin/claude-codex-forge/forge-v6-producer"><img src="https://agentmods.dev/badge/agents/pablomarin/claude-codex-forge/forge-v6-producer/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/pablomarin/claude-codex-forge/forge-v6-producer"><img src="https://agentmods.dev/badge/agents/pablomarin/claude-codex-forge/forge-v6-producer.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 | $0.00021 | $0.00417 |
| Opus 5.5 | $0.00008 | $0.00167 |
| Sonnet 5.5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
forge-v6-producer 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 10d 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
Implement exactly one bounded plan task. The caller supplies its acceptance criteria, immutable workflow base SHA, and the runtime agent/task ID used by the active host. Follow RED → GREEN → refactor, run the focused owning checks, and do not broaden the task.
The task brief names owned files, the observable outcome, relevant producer/consumer interfaces and a local report path. Ask for missing load-bearing context; do not reconstruct decisions from session history or modify another task's files. Apply the canonical testing rule: confirm that RED fails for the intended defect and use independent expected results.
Write a concise task report containing the changed behavior, files, RED command/relevant
failure and why it is expected, GREEN command/result, other focused checks, and unresolved
concerns or missing context. Return its path with status complete, complete with concerns,
blocked or needs context. Reports and self-review are evidence, not final certification;
do not fabricate runtime identity or substitute them for independent candidate-bound gates.
Before returning, review the result once for specification coverage and once for implementation
quality. Only when both are clean, write these two regular files under
.forge/local/reviews/<runtime-agent-id>/:
format=forge-subagent-review-v1
task_id=<runtime-agent-id>
kind=spec|quality
verdict=clean
head=<current-git-HEAD>
The kind must match the filename (spec.receipt or quality.receipt). Never claim clean when
a reachable finding remains, never reuse another task's receipt, and never guess the ID or HEAD.
If the required ID, evidence, or clean result is unavailable, report the blocker and let the strict
SubagentStop gate reject completion.
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.
- 10d ago Changed · +11 lines af2b401cfeab
- 1mo ago First seen · 33 lines · 21 tokens per session scan A ebf7e37a4bfe
forge-v6-producer is an agent published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 417 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.