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 skills add OutlineDriven/outline-driven-development --skill agent-surface-forgegit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/skills/outlinedriven/outline-driven-development/agent-surface-forge)<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/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/skills/outlinedriven/outline-driven-development/agent-surface-forge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/agent-surface-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 99 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00056 | $0.03922 |
| Opus 5.5 | $0.00022 | $0.01569 |
| Sonnet 5.5 | $0.00011 | $0.00784 |
| Haiku 4.5 | $0.00006 | $0.00392 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-surface-forge — 100% identical, 92 lines differ
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) orimprove. 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 withautoFix: 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 ofplugin,agent,skill,docs,prompt,claudemd,hooks,cross-file. Unknown values are rejected.- Target skill path (required, improve mode): a path to a
SKILL.mdfile or a skill slug that resolves to one by searchingskills/. - 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_TOKENis supplied by the operator environment, never requested or stored by this workflow.
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.
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 Changed · +54 lines · -23 tokens per session 563440f1c033
- 1mo ago First seen · 74 lines · 79 tokens per session scan A 5e7e0222ab73
agent-surface-forge is a skill published in the GitHub repository OutlineDriven/outline-driven-development (54 stars, last pushed 28d ago), licensed Apache-2.0. It adds 56 tokens to every session and 3,922 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 2026-09-03.
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".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
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.
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.
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.