A workflow for safely changing an existing Pocket Skill, a reusable set of instructions for an AI agent. It preserves its existing details unless you explicitly change them and refreshes the local registration.

Use it to locate and edit a Pocket Skill in its repository, then make the revised version available locally.

It lowers the risk of accidentally changing metadata, editing the wrong skill, or leaving the updated skill unavailable.

edit-skill — Skill by RongchangLi

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/rongchangli/pocketskill/edit-skill

Any agent

npx skills add RongchangLi/pocketskill --skill edit-skill

Clone the repo

git clone --depth 1 https://github.com/RongchangLi/pocketskill

Made for: Claude Code, Codex.

Or install my-skill, the plugin that ships this one along with the rest of its 12 skills.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 867 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.

Model	Per session	Once invoked
Fable 5	$0.00023	$0.00867
Opus 5	$0.00012	$0.00434
Sonnet 5	$0.00005	$0.00173
Haiku 4.5	$0.00002	$0.00087

Measured 2d ago against content hash a3369212fa3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

edit-skill 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 2d 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.

plugins/my-skill/skills/manage-skills/edit-skill/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

When the user invokes this skill, edit an existing Pocket Skill in their local library.

Tool Expectations

This workflow may use shell commands and git status checks.

All operations must happen from the pocketskill repository root. First locate it:

Use the current working directory if it contains plugins/my-skill/skills/ and install.sh.
Otherwise search upward from the current working directory.
If no root is found, ask the user for the pocketskill path and stop until they provide it.

Workflow

1. Identify The Target

If the user did not name a skill, list directories under plugins/my-skill/skills/my-skills/ and plugins/my-skill/skills/private-skills/ that contain SKILL.md, then ask which one to edit.
Never list or offer skills from plugins/my-skill/skills/manage-skills/. Built-in management skills cannot be edited through this skill.
Skip .DS_Store, cache files, and directories without SKILL.md.
If the user explicitly names a skill in manage-skills/, refuse with the message "Built-in management skills cannot be edited directly."
Confirm the target path is exactly <repo-root>/plugins/my-skill/skills/<parent-dir>/<skill-name>/SKILL.md where <parent-dir> is my-skills or private-skills.
If the target does not exist, stop and suggest create-skill.

2. Inspect Before Editing

Read the target SKILL.md and identify:

frontmatter name
frontmatter description
whether the body still looks like the template placeholder
whether the skill is public (my-skills/) or private (private-skills/)
whether SKILL.md has grown into a large all-in-one document that should be split into task-specific references/*.md

If the user wants to rename the skill or change the directory name, use rename-skill instead of editing in place.

3. Edit Safely

Change only the target SKILL.md unless the user explicitly asks for related docs.
If the user asks to reduce context usage, modularize the skill, or add substantial long-form guidance, you may create or update files under the target skill's own references/ directory.
Preserve frontmatter name unless the user explicitly asks to change display metadata without renaming the directory.
Keep description short and trigger-oriented.
Do not change the skill's public/private status by moving directories.
Do not add secrets, tokens, passwords, internal credentials, or private URLs.

Read the full file on GitHub · 77 lines

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.

2d ago First seen · 77 lines · 23 tokens per session scan A a3369212fa3c

Subscribe to this mod's changes

edit-skill is a skill published in the GitHub repository RongchangLi/pocketskill (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 867 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 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens