mode
Skill16 starsChanged 7 months agoMITView on GitHub
Switch Claude's tool access mode for the session. Modes limit which tools Claude will use — useful for reviewing code without risk of edits, or ensuring no shell commands run. Triggers on "Mode develop", "Mode review", "Mode safe", "Mode deploy", "/mode", "switch to review mode", "read only mode", "safe mode".
11 other projects use a version of this.
Adopted by
Most recently taken up by
- agoopintsai/shiprighttheir own version, first seen Nov 1, 2026
- Edmonds-Commerce-Limited/claude-code-hooks-daemontheir own version, first seen Oct 28, 2026
- eprouveze/claude-skillstheir own version, first seen Oct 20, 2026
- Scylla23/modelroutertheir own version, first seen Oct 20, 2026
- ProjectAJ14/eklavyatheir own version, first seen Oct 20, 2026
- DATA-AI-XYZ/Tandemtheir own version, first seen Oct 15, 2026
Used with
Projects with it also use setup.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- ProjectAJ14/eklavya★ 29same name
- Edmonds-Commerce-Limited/claude-code-hooks-daemon★ 4same name
- LarryStanley/pi-delegate★ 4same name
- agoopintsai/shipright★ 2same name
- ahamedzoha/atelier★ 2same name
- ibahgat/oh-my-iflow★ 2same name
- lukasrepublic/agentic-foundry★ 1same name
- Scylla23/modelrouter★ 1same name
- StakeholderSensei/polygraph★ 1same name
- DATA-AI-XYZ/Tandem★ 0same name
1 more not listed
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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- actSkill
- security-checkSkill
- environment-checkSkill
- run-verificationSkill
- refactorSkill
- debug-session-archivedSkill
- generate-guardsSkill
- check-anthropicSkill
- code-reviewerSkill
- code-reviewSkill
- debug-sessionSkill
- end-sessionSkill
- evolve-checkSkill
- evolveSkill
- fix-bugSkill
- forgetSkill
- frontend-designSkill
- guardSkill
- kit-healthSkill
- learnSkill
- map-codebaseSkill
- parallel-prototypesSkill
- planSkill
- powershell-safeSkill
- product-riskSkill
- progress-reportSkill
- prototype-hypothesisSkill
- recallSkill
- refactoring-uiSkill
- scan-codebaseSkill
- scan-conventionsSkill
- search-firstSkill
- search-memorySkill
- shadow-codeSkill
- skill-creatorSkill
- smart-resumeSkill
- start-sessionSkill
- strategic-compactSkill
- tourSkill
- ux-heuristicsSkill
- verification-loopSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
If no mode is specified, list the 4 options and ask which one.
- Very specific: line 34
Write the mode name to .claude/memory/tasks/current_mode.txt (create if needed).
- Very specific: line 58
No settings.json changes — mode is behavioral, not a permission file change
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: mode
Trigger: "Mode [develop|review|safe|deploy]" · "/mode" · "switch to review mode" · "read only mode" · "safe mode"
Modes
| Mode | Tools available | When to use |
develop | All tools (default) | Normal coding sessions — full read/write/bash access |
review | Read, Glob, Grep only | Reviewing code, auditing, reading without risk of changing anything |
safe | Read, Edit, Write, Glob, Grep — no Bash | Making changes but no shell commands (no running scripts, no installs) |
deploy | Read, Glob, Grep, Bash (deploy scripts only) | Production deploys — read + restart/deploy commands only, no source edits |
Steps
Step 1 — Parse the mode
Extract the mode name from the trigger: develop, review, safe, or deploy.
If no mode is specified, list the 4 options and ask which one.
Step 2 — Write mode file
Write the mode name to .claude/memory/tasks/current_mode.txt (create if needed).
Step 3 — Announce and self-enforce
Output a clear announcement and self-enforce the constraints for the rest of the session:
develop:
Mode: DEVELOP — Full access. All tools available. (This is the default.)
review:
Mode: REVIEW — Read-only. I will only use Read, Glob, and Grep for the rest of this session. No edits, no writes, no shell commands — even if asked. To restore full access: "Mode develop".
safe:
Mode: SAFE — No shell. I will use Read, Edit, Write, Glob, Grep only. No Bash commands for the rest of this session — even if asked. To restore full access: "Mode develop".
deploy:
Mode: DEPLOY — Deploy only. I will use Read, Glob, Grep, and Bash (deploy/restart scripts only). No source file edits for the rest of this session. To restore full access: "Mode develop".
Step 4 — Enforce for the session
For the rest of the session, do not use any tool outside the active mode's allowed list — even if the user asks. If a restricted tool is needed, say: "Current mode is [X] — that tool is restricted. Say 'Mode develop' to restore full access, or confirm you want to proceed."
Notes
- Mode resets to
developon the next session start - No settings.json changes — mode is behavioral, not a permission file change
Mode developalways restores full access immediately
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.