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 agentmods add instructions/strml/cc-tab-titles/claude-mdgit clone --depth 1 https://github.com/STRML/cc-tab-titlesWrote 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/instructions/strml/cc-tab-titles/claude-md)<a href="https://agentmods.dev/instructions/strml/cc-tab-titles/claude-md"><img src="https://agentmods.dev/badge/instructions/strml/cc-tab-titles/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00745 | $0.00745 |
| Opus 5 | $0.00373 | $0.00373 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
cc-tab-titles CLAUDE.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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc-tab-titles
A Claude Code plugin that sets terminal tab titles to AI-generated summaries of what's being worked on.
Project Structure
hooks/
hooks.json # Hook definitions (SessionStart, Stop, UserPromptSubmit)
set-tab-title.sh # Stop hook: generates summary via claude -p (Haiku), writes OSC title
session-start.sh # SessionStart hook: claims tab ownership for new session
restore-title.sh # UserPromptSubmit hook: re-applies saved title after Claude resets it
statusline.sh # Optional statusLine command to keep title persistent
lib/
project-slug.sh # compute_project_slug(): CamelCase 2-chars-per-word slug
session-title.sh # last_custom_title(): reads the user's /rename title from the transcript
tests/
run-tests.sh # Runs every test-*.sh
test-project-slug.sh
test-session-start.sh
test-session-title.sh
lib/assert.sh # Tiny test helpers
No build system or package manager — pure bash. Run bash tests/run-tests.sh.
Key Architecture Decisions
- Non-blocking:
set-tab-title.shspawns a background subshell (disown) to avoid blocking Claude Code - Tab ownership: Uses
/tmp/claude-tab-titles/owner-<TAB_KEY>to guard against stale writes landing in a new session's tab - TTY detection: Prefers
$CMUX_SURFACE_ID(cmux multiplexer); falls back tostat -f '%Lr' /dev/tty - Title persistence: Saved to
/tmp/claude-tab-titles/<session_id>; restored on UserPromptSubmit with 0.5s delay - Haiku model:
claude-haiku-4-5-20251001with--effort lowand all hooks/sessions/tools disabled for speed /renameoverride:/rename <name>writes{"type":"custom-title","customTitle":...}to the transcript (it fires no hook). The hooks read that, suppress Haiku, and record a<session>.renamemarker until the user renames to a different value. Auto-generated"ai-title"entries are ignored — only explicit renames win. Behavior differs by terminal:- cmux already displays the renamed session natively, so the hooks just clear cc-tab-titles' own override (
cmux tab-action --action clear-name) and defer to cmux — they do not set a competing title. session-start.sh does the same when resuming an already-named session, avoiding a project-name flash. - Other terminals have no native session name, so the rename value is written to the tab title via OSC.
- cmux already displays the renamed session natively, so the hooks just clear cc-tab-titles' own override (
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.
- 5d ago First seen · 50 lines · 745 tokens per session scan A ad952d8b2cc4
cc-tab-titles CLAUDE.md is an instructions file published in the GitHub repository STRML/cc-tab-titles (2 stars, last pushed 2mo ago), licensed MIT. It adds 745 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).