mocapi CLAUDE.md

Project instructions for Mocapi, including its development workflow, documentation layout, and rules for architecture records. An ADR is a short document explaining an important architecture decision.

In plain words
What is it for?
Use them when planning Mocapi changes, deciding whether an ADR or design document is needed, organizing documentation, or following its rule against unapproved code edits.
Why use it?
They tell contributors where documentation belongs and when code changes require matching design or decision updates.

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/callibrity/mocapi/claude-md
Clone the repo
git clone --depth 1 https://github.com/callibrity/mocapi
Per session 1,403 This file is loaded in full into every session.
When invoked 1,403 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 $0.01403 $0.01403
Opus 5 $0.00701 $0.00701
Sonnet 5 $0.00281 $0.00281
Haiku 4.5 $0.00140 $0.00140

Measured 2d ago against content hash 7a0a3a443493, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mocapi 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude notes for mocapi

Project-specific overrides and additions. Global workflow, code-quality, and OSS release process live in ~/CLAUDE.md (see # OSS Release Process there).

Workflow

Never write or edit code without being explicitly told to do so! You may ask if you are allowed to make changes, but do not do so unless I explicitly confirm.

When committing and pushing changes to CLAUDE.md only, include [skip ci] in the commit message to avoid triggering CI.

Documentation layout

Docs live under docs/ in three trees:

  • docs/guides/ — user-facing how-tos for library consumers.
  • docs/design/ — living design docs describing the current architecture; updated in lockstep with the code.
  • docs/adr/ — Architecture Decision Records (point-in-time, status: Accepted/Superseded/etc.). Template at docs/adr/_template.md.

The Ralph spec workflow has been retired; the historical specs that produced 0.1.0 → 0.17.0 were mined for ADRs and removed from the tree.

New non-trivial work follows the superpowers SDD pipeline — see docs/superpowers/README.md for when it applies and where spec/plan artifacts live.

When a change requires an ADR + design-doc update (rule)

Before writing code for an architecturally significant change, stop and produce two artifacts. "Architecturally significant" means the change falls into any of these buckets:

  • A new module, or removal/merger of an existing module.
  • A new SPI (interface intended for users to implement) or a backwards-incompatible change to an existing SPI.
  • A new transport, or a change to the McpServerMcpTransport contract.
  • A change to handler discovery, customizer composition, the stratum ordering, or the descriptor pattern.
  • A change to session storage, mailbox/journal usage, or the Substrate SPI contract.
  • A change to the authorization model (filter chains, Guard semantics, McpTokenStrategy, RFC 9728 metadata shape).
  • A change to what mocapi declares not implemented in docs/adr/0018-*.md (adding/removing an item from the list).
  • A change to declared MCP capabilities (subscribe, listChanged, etc.).

Read the full file on GitHub · 116 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 · 116 lines · 1,403 tokens per session scan A 7a0a3a443493

Subscribe to this mod's changes

mocapi CLAUDE.md is an instructions file published in the GitHub repository callibrity/mocapi (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,403 tokens to every session, about $0.0070 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.