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/emson/claudoro/claude-mdgit clone --depth 1 https://github.com/emson/claudoroWrote 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/emson/claudoro/claude-md)<a href="https://agentmods.dev/instructions/emson/claudoro/claude-md"><img src="https://agentmods.dev/badge/instructions/emson/claudoro/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 | $0.02720 | $0.02720 |
| Opus 5 | $0.01360 | $0.01360 |
| Sonnet 5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
claudoro CLAUDE.md scanned grade A with 1 finding 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
(`path`, `os`, `fs`, `child_process`) — identical code on macOS, Linux, Windows (D-005). How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudoro
A Pomodoro timer that lives inside the Claude Code terminal: a live, ticking countdown in the
status line plus a render-decoupled end-of-block alarm. Open source, distributed as
npm install -g claudoro with a thin Claude Code plugin wrapper.
Read first: specs/spec.md (architecture, modules, data model, acceptance tests) and
specs/decisions.md (D-001..D-012, the authoritative rationale). The spec supersedes
specs/charter.md where they disagree. When in doubt, the decisions log wins.
Core principle
The code must always be robust, flexible, and elegant.
One architectural truth underpins everything (D-001): the pomo CLI is the single source of
truth. It owns all state, scheduling, and history. The status line, the /pomo command, and the
alarm are thin surfaces over it. The CLI runs with zero model involvement, so the core feature never
costs API tokens.
A second truth makes mutation safe (D-007): derive, do not store, aggregates. Counts, cycle
position, focus minutes, and streaks are folded from immutable records on read. There are no mutable
counters, so undo/restore are correct by construction.
How we write code
Functional-first, composition over cleverness. Favour small, pure, well-named functions composed into larger behaviour. Avoid complex code; if a function is hard to name or test, split it.
- Pure core, impure edges. Keep logic (timer math, derivation, rendering, formatting) as pure
functions of their inputs. Push side effects (file I/O,
flock,spawn, clock, stdout) to a thin boundary layer. A function reads the clock once and passesnowdown; it does not callDate.now()deep in a fold. - Compose, don't branch-pile. Build a verb from discrete subfunctions
(
resolvePaths → readState → mutate → writeAtomic), not one long procedure. Prefermap/filter/reduceand data transformation over imperative mutation. - Data in, data out. Functions take plain values and return plain values. Immutable updates
(
{...state, run_state: 'paused'}), no in-place mutation of shared objects. - Total functions. Handle the empty/missing/corrupt case in the function, not at the call site.
Missing state →
idle; corrupt JSON → quarantine + reinit; never throw on the render path. - Explicit over implicit. No hidden globals, no ambient singletons. Dependencies (paths, clock, fs) are passed in, which also makes them trivially mockable in tests.
- Small modules with one job, mirroring the spec's M1..M10. A file should fit in your head.
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.
- 4d ago First seen · 154 lines · 2,720 tokens per session scan A 4282f5394e87
claudoro CLAUDE.md is an instructions file published in the GitHub repository emson/claudoro (48 stars, last pushed 1mo ago), licensed MIT. It adds 2,720 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
wasp AGENTS.md
AGENTS.md instructions for wasp-lang/wasp, covering wasp monorepo, contribution policy, repository structure, build & development and code conventions.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
core AGENTS.md
AGENTS.md instructions for module-federation/core, covering agents.md, scope and precedence, source of truth (in priority order), environment parity and worktree mode (required in worktrees).
std-env AGENTS.md
AGENTS.md instructions for unjs/std-env, covering agents, project overview, maintenance, scripts and source structure.
dom-docx AGENTS.md
Instructions for floodtide/dom-docx, covering agent guide: html → docx (dom-docx), design goal for agents, what converts best, tier 1 — excellent (90–96% visual fidelity) and tier 2 — good (80–92%).