verbosity
Skill17 starsChanged 37 days agoMITView on GitHub
Response verbosity protocol: reads the level from ~/.claude/memory/verbosity.md and applies the MIN, INFO or VERBOSE output rules to every reply
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- project-template/CLAUDE.mdCLAUDE.md
- agent-delegationSkill
- code-simplifierSkill
- critical-reviewSkill
- memory-firstSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read ~/.claude/memory/verbosity.md once at the start of every session.
- Very specific: line 25
All applicable tags: [CHANGES], [REASON], [PLAN], [BUG].
- Very specific: line 32
Read ~/.claude/memory/verbosity.md for the configured level.
≈ “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
Verbosity
Read ~/.claude/memory/verbosity.md once at the start of every session. Extract the value after VERBOSITY:. Default to MIN if the file is absent or the value is unrecognized.
Levels
MIN (default)
- One declarative sentence per response.
[CHANGES]tag: list of files modified only. No prose explanation unless the user asks.- On failure or ambiguity: one clarifying question. Nothing else.
INFO
- Bullet list: what changed and why. Max 5 bullets.
- Tags:
[CHANGES]+[REASON]. - No prose paragraphs.
VERBOSE
- Full explanation. Prose allowed.
- All applicable tags:
[CHANGES],[REASON],[PLAN],[BUG]. - No length limit.
Application
The active level is enforced by a UserPromptSubmit hook (verbosity-remind.sh) that fires before every response and injects a compact, level-aware reminder into the conversation context. The reminder is injected at each prompt boundary so the constraint survives context fills and session drift — not only at session start.
Read ~/.claude/memory/verbosity.md for the configured level. Default: MIN if the file is absent, unreadable, or contains no valid VERBOSITY: token. To change the level, re-run the installer with --verbosity MIN|INFO|VERBOSE or edit the file directly.
Changes to verbosity.md take effect on the next user prompt — no session restart required. If you edit the file during an active Claude session, the hook picks up the new level on the immediately following prompt; there is no stale session state to clear. If the hook emits at an unexpected level after a change, verify the file was saved (not merely modified in an unsaved buffer), confirm that $HOME resolves to the expected path in the terminal that launched Claude, and check that no parent environment is setting CC_VERBOSITY_SKIP=1.
VERBOSITY_HOOK_VERSION: 1.11.0
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.