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 Firstp1ck/pi-coding-agent-forge --skill patch-mdgit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-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/skills/firstp1ck/pi-coding-agent-forge/patch-md)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/patch-md"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/patch-md/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/firstp1ck/pi-coding-agent-forge/patch-md"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/patch-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01531 |
| Opus 5.5 | $0.00018 | $0.00612 |
| Sonnet 5.5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
patch-md 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patch MD Skill
When to Use
Use this skill to:
- create or update a patch package;
- migrate a legacy prose-only
PATCH.mdto schema v2; - inspect patch status after package updates;
- plan, apply, verify, or roll back a patch;
- reapply a patch across machines or package layouts.
Required v2 Artifact
A trusted patch package contains:
PATCH.md
patch.manifest.json
scripts/<lifecycle-handler>.mjs
Tests and fixtures are required for package-version or layout-dependent patches.
PATCH.mdexplains intent, scope, transformations, verification, rollback, and limitations.patch.manifest.jsonis the machine-readable source of truth.- The lifecycle handler discovers actual runtimes and implements semantic, idempotent transformations.
Use PATCH-TEMPLATE.md, TOOL-CALL-SPEC.md, and patch-manifest-v2.schema.json.
App-specific package location
For an app-specific patch, the app's verified configuration/home directory is the canonical package location, normally <app-config>/patches/<patch-id>/.
- Resolve the actual config/home from the app's documented runtime settings, launch options, or verified environment overrides before assuming a default. Ask when the location cannot be established safely.
- Save the complete reconstructable package there:
PATCH.md, manifest, lifecycle handlers, transformation profiles/assets, documentation, and required tests/fixtures. Do not deliver only a note that depends on a checkout, temporary capture, or versioned app-install directory. - A repository may retain a development mirror, but report the app-config package as the canonical artifact. Keep runtime assets package-relative and verify the copied package independently.
- For T3 Code, use its resolved T3 home (
T3CODE_HOMEwhen configured, otherwise the verified~/.t3default), for example~/.t3/patches/<patch-id>/. Keep patch artifacts outside liveuserdata; storing a patch never authorizes editing app settings or runtime state. - Do not silently move existing patches, receipts, or backups. Preserve their explicit state directory for rollback, and use
--state-dirwhen a separately chosen config-local state directory is intended. - Patch storage is not patch application. After an app update, run fresh read-only status/plan and obtain plan-bound approval before any installed mutation; never silently reapply.
What ships with it
7 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.
- 22d ago Changed · +12 lines f686e7c9e960
- 2mo ago First seen · 148 lines · 45 tokens per session scan A e187c9ab11e7
patch-md is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (93 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 1,531 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 2026-08-30.
Other skills, from other repositories
ae-ltd-worktree-mesh
Use when parallel branches are needed for feature work, hotfixes, or review fixes using git worktrees with minimal context switching. AE.LTD workflow for safe creation, usage, and cleanup.
commit-pr
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before git push, gh pr create, gh pr edit, or gh pr ready. Routes to the single…
fork-pr-operations
Operational patterns for fork PRs (head repo differs from base repo). Covers GitHub workflow approval after push, force-push protocol, remote naming conventions, stale CI verification, and bot review multi-round awareness. Load when working with fork PRs, cross-repo contributions, or workflow approval issues.
merge-queue-readiness
Pre-queue merge-group CI simulation. Triggered before adding a PR to a GitHub merge queue. Prevents merge-queue kick-outs from integration test failures.
contributing
Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.
git-clean-gone-branches
Clean up local branches whose remote tracking branch is gone. Use when the user says "clean up branches", "delete gone branches", "prune local branches", "clean gone", or wants to remove stale local branches that no longer exist on the remote. Also handles removing associated worktrees for branches that have them.