clisbot CLAUDE.md

Repository-wide instructions for clisbot, including which architecture documents define its implementation rules and the order in which an agent should read them.

In plain words
What is it for?
Use them before feature, task, onboarding, operator, or research work to find the right project documentation and decide how to handle architecture conflicts.
Why use it?
They prevent changes from drifting away from the documented architecture and clarify when a conflict requires asking the user.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/longbkit/clisbot/claude-md
Clone the repo
git clone --depth 1 https://github.com/longbkit/clisbot
Per session 1,889 This file is loaded in full into every session.
When invoked 1,889 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01889 $0.01889
Opus 5 $0.00945 $0.00945
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 2d ago against content hash 6e3421aacbb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clisbot 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 2d 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.

CLAUDE.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Scope

These rules apply to everything inside this repository.

The stable implementation contract lives in:

  • docs/architecture/architecture-overview.md
  • docs/architecture/surface-architecture.md
  • docs/architecture/runtime-architecture.md
  • docs/architecture/domain-language.md

If implementation conflicts with those docs:

  1. stop
  2. refactor toward the docs if the fix is clear
  3. ask the user before proceeding if the conflict changes behavior, architecture, or scope

Do not silently drift away from the architecture docs.

First Read Order

Load context in this order unless the task is obviously narrower:

  1. README.md
  2. docs/overview/README.md
  3. the architecture docs listed above

Then load only the smallest extra context that matches the task:

  • feature work: docs/features/README.md, the relevant feature doc, then linked task docs
  • task execution: docs/tasks/README.md, docs/tasks/backlog.md, then the relevant task doc
  • operator or onboarding or release work: docs/development/README.md and the relevant user-guide doc
  • research-heavy questions: the relevant file under docs/research/

Do not front-load the whole docs tree.

Documentation Precedence

When documents disagree, use this order:

  1. docs/architecture/
  2. README.md, docs/development/README.md, and docs/user-guide/
  3. docs/features/
  4. docs/tasks/
  5. docs/research/ and docs/lessons/

docs/research/ and docs/lessons/ are supporting context only. They should not silently override architecture or guide docs.

Repo Map

Use this ownership map before editing:

  • src/channels: Slack and Telegram surfaces, route handling, rendering, pairing, follow-up behavior
  • src/agents: durable agent state, sessions, queueing, loops, attachments, run lifecycle
  • src/auth: roles, permissions, owner claim, authorization resolution
  • src/config: schema, loading, credentials, templates
  • src/control: operator CLI, runtime lifecycle, health, status, logs, bootstrap
  • src/runners: execution backends, currently tmux
  • src/infra: small host/runtime primitives only, with no product concepts
  • test/: regression and behavior coverage
  • docs/tests/: readable validation scenarios when behavior needs explicit ground truth

Read the full file on GitHub · 191 lines

Changes

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.

  1. 2d ago First seen · 191 lines · 1,889 tokens per session scan A 6e3421aacbb0

Subscribe to this mod's changes

clisbot CLAUDE.md is an instructions file published in the GitHub repository longbkit/clisbot (114 stars, last pushed 2d ago), licensed MIT. It adds 1,889 tokens to every session, about $0.0094 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 2026-08-30.