agent-surface-forge

agent-surface-forge is a skill for Claude Code, Codex from OutlineDriven/outline-driven-development. It costs 56 tokens per session (3,922 once invoked), scanned A, original, Apache-2.0.

An audit and repair tool for the files that guide coding agents, including agent definitions, skills, prompts, hooks, and project instructions. It reports findings with confidence levels and can apply selected high-confidence fixes.

In plain words
What is it for?
Use it to review agent configuration and documentation, then apply narrowly scoped fixes to high-confidence problems.
Why use it?
It helps find unclear, stale, or conflicting instructions that can make an agent behave inconsistently.

Skill for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

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 skills/outlinedriven/outline-driven-development/agent-surface-forge
Any agent
npx skills add OutlineDriven/outline-driven-development --skill agent-surface-forge
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-surface-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/agent-surface-forge.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/agent-surface-forge)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/agent-surface-forge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/agent-surface-forge.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,922 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 5.1 $0.00056 $0.03922
Opus 5 $0.00028 $0.01961
Sonnet 5 $0.00011 $0.00784
Haiku 4.5 $0.00006 $0.00392

Measured today against content hash 563440f1c033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-surface-forge 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 today.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.devin/skills/agent-surface-forge/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent surface forge

Contract

Field Bound contract
Trigger User asks to audit or repair agent surfaces, plugin configs, agent definitions, skills, CLAUDE.md/AGENTS.md, docs, prompts, commands, or hooks; or asks to iteratively improve one skill, fix skill-quality findings, or resolve scanner alerts (W001, W011, W012) on a skill.
Authority Reversible local: audit mode writes only HIGH-certainty autoFix:yes findings on the named plugin/agent/skill/docs/prompt/claudemd/hooks surfaces under --apply; improve mode writes only files within the resolved skill directory; rollback is reverting any applied edit whose re-analysis introduces a new HIGH finding or restoring prior file content. No remote mutation.
Side effect Local file edits to HIGH + autoFix:yes items only under --apply, or minimal contract-preserving edits inside one skill directory in improve mode; re-verifies after each edit. No suppression state, no model routing, no external analyzer binary outside scanner remediation.
Done Audit mode: surface audit report produced with all HIGH findings complete in default output, MEDIUM/LOW shown only under --verbose, and under --apply each HIGH finding removed without new HIGH issues. Improve mode: a final review contains no critical or major findings and finalization edits pass scope and regression checks, or a non-success terminal status is reported without being presented as convergence; scanner remediation ends on a clean scan with information preserved and the pre-authoring checklist passed.

Inputs

  • mode (optional): audit (default) or improve. Audit runs the multi-surface sweep; improve runs the deep single-skill loop.
  • target (optional, audit mode): path to audit; defaults to .. Taken from the first non-flag argument.
  • --apply (optional flag, audit mode): apply only HIGH-certainty findings with autoFix: yes. Absent means report only.
  • --verbose (optional flag): include MEDIUM and LOW findings. Default output shows HIGH plus MEDIUM/LOW summary counts.
  • --focus=<type> (optional, audit mode): comma-separated subset of plugin, agent, skill, docs, prompt, claudemd, hooks, cross-file. Unknown values are rejected.
  • Target skill path (required, improve mode): a path to a SKILL.md file or a skill slug that resolves to one by searching skills/.
  • Improvement scope (optional, improve mode): specific findings to fix, remaining findings from an interrupted run to resume, or quality dimensions to focus on. When the scope is scanner alerts, the scan output listing each alert as a code with its file, or the skill directory to scan to produce one. Optional SNYK_TOKEN is supplied by the operator environment, never requested or stored by this workflow.

Read the full file on GitHub · 128 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · +54 lines · -23 tokens per session 563440f1c033
  2. 2d ago First seen · 74 lines · 79 tokens per session scan A 5e7e0222ab73

Subscribe to this mod's changes

agent-surface-forge is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 3,922 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

audit-project

Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".

OutlineDriven/odin-claude-plugin · 50 tokens

duet

Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.

OutlineDriven/odin-claude-plugin · 28 tokens

goal-prompt-drafting

Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.

OutlineDriven/odin-claude-plugin · 57 tokens

handoff-prompt

Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.

OutlineDriven/odin-claude-plugin · 62 tokens

drill

Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.

OutlineDriven/odin-claude-plugin · 67 tokens

snippet-image-rendering

Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.

OutlineDriven/odin-claude-plugin · 64 tokens