edit-config
Skill261 starsChanged 56 days agoMITView on GitHub
Inspect, add, change, remove, repair, or update Claude and Codex configuration from Mizoreww/awesome-agent-config on main. Use for configuration queries and edits, installed skills/plugins/rules/MCP, and changes to this repository's configuration templates or catalogue.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Mizoreww/awesome-agent-configword for word, first seen Sep 17, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Mizoreww/awesome-agent-config★ 261100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- storage-analyzerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 34
Repository configuration: follow MAINTAIN.md for templates, skills, catalogue entries, recommendations, and documentation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Edit agent configuration
This skill serves both Claude and Codex and tracks one repository branch:
- Repository:
https://github.com/Mizoreww/awesome-agent-config.git - Branch:
main
1. Identify the request and target
Distinguish inspection from modification, and repository edits from changes to an installed agent. Default to the current conversation's agent; target both only when requested. Resolve the actual CLAUDE_CONFIG_DIR, CODEX_HOME, or user-selected home. Read relevant configuration, agent-config/selection.json, and agent-config/files.json when present; use native lists to verify installed state. Redact credentials.
For inspection, report current values, selected content, sources, differences, and pending items directly in the conversation as relevant. Export a document only when requested. Reading configuration does not authorize writing receipts, changing settings, installing dependencies, or disabling imports. Stop when the query is answered unless the user also requested a change.
Completion: the operation, target, existing state, and authorization are clear.
2. Resolve the branch for changes
Fetch the branch above into a fresh temporary checkout and resolve its full commit SHA. Use files from that same SHA throughout an installation/update operation. Preserve existing user checkouts and local edits. A missing branch or incompatible layout is an error; report it without substituting another branch or the remote default.
For installed configuration, compare the receipt's repository URL and update policy with this target. Read repository identity and migration from the resolved source: equivalent HTTPS/SSH URLs and the documented repository rename identify the same source. Matching branch records can proceed; a default-branch policy can proceed when the remote default resolves to main, preserving that policy. Missing source metadata uses this skill's explicit target without inventing installation ownership. A conflicting fork, branch (including agent-config-for-agents), pinned commit, or local source remains unchanged until the user chooses migration; reuse an already explicit migration request instead of asking again. Record the previous source when migrating, and keep all selections, hashes, and backups.
For repository edits, use the user's designated checkout on main or their chosen work branch, verify its repository and branch, and read its current MAINTAIN.md. Preserve authorized uncommitted changes and work with them. Installation changes still use a single resolved source as described above.
Completion: the source, revision, and any source migration are established.
3. Apply the requested operation
- Installed configuration: read
INSTALL.md,catalog.md, and the target platform's README from the resolved source. Follow their native plugin/MCP, protected file, and verification procedures. Default to recorded selections. For additions or changed selections, followINSTALL.md'schoose-optionsprocedure: show the target agent's complete supported catalogue directly in the conversation, with category grouping, continuous item numbers, useful descriptions, author recommendations and installed status. Prefer a real multi-select question tool when available; otherwise accept multiple numbers or names in chat. Export a selection document only when requested. Reuse explicit choices; wait for an actual response when choices are missing. Recommendations do not authorize installation. - Repository configuration: follow
MAINTAIN.mdfor templates, skills, catalogue entries, recommendations, and documentation. Editing repository files does not modify an agent home.
Handle retired or renamed IDs using docs/migration.md. Omitted selections remain installed. Removal requires an explicit request and ownership checks. Preserve upstream revision constraints, local customizations, credentials, hooks, memory databases, and each agent's real lessons. Continue within the user's existing authorization.
Completion: each requested change has an actual result, including failures and pending steps.
4. Verify and record
Verify the changed files or native resources. For installed changes, record the canonical repository.url, actual repository.revision, and the policy established in step 2: repository.update = {"kind":"branch","ref":"main"} for the explicit target, or the retained {"kind":"default-branch"} policy. Preserve previous source metadata when normalizing the renamed URL, plus per-item revisions and provenance. Repository edits follow their own commit and validation workflow. A repository version alone does not establish installation success.
Report what changed and what remains pending. Keep the two agent homes and their records independent. The old update-config / update_config names migrate to this skill through the repository's migration instructions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.