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/sralli/agendum/claude-mdgit clone --depth 1 https://github.com/sralli/agendumWhat 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 | $0.00761 | $0.00761 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
agendum 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agendum
Project memory and scoping engine for AI coding agents. Python 3.13+, uv, FastMCP.
Workflow
agendum augments the harness (Claude Code + superpowers + plan mode). It does NOT compete with it.
Separation of concerns
| Concern | Owner |
|---|---|
| Brainstorming & design | Superpowers (brainstorming skill) |
| Planning & task breakdown | Superpowers (writing-plans) + plan mode |
| Subagent dispatch | Claude Code Agent tool |
| Persistent project state | agendum |
| Bounded work packages | agendum |
| Cross-session memory | agendum |
| Project board / backlog | agendum |
The flow
1. PLAN (harness) brainstorming → writing-plans → plan file
2. INGEST (agendum) pm_ingest reads plan → creates bounded board items
3. SCOPE (agendum) pm_next returns scoped work package with context
4. EXECUTE (harness) Agent works within the scoped package
5. REPORT (agendum) pm_done records completion, decisions, patterns
6. RESUME (agendum) Next session: pm_status → pm_next → continue
When to skip agendum
- Single-line fixes (typos, version bumps)
- Pure research/exploration (no code changes)
Quick reference
uv run pytest # all tests must pass
uv run ruff check src/ tests/ # lint
uv run ruff format . # format
Architecture
- 11 MCP tools in
tools.py - 4 stores: BoardStore, ProjectStore, MemoryStore, LearningsStore
- Enrichment pipeline:
enrichment/pipeline.py+enrichment/sources.py - All writes use
get_lock()+atomic_write()fromstore/locking.py - Board items: Markdown + YAML frontmatter in
.agendum/projects/<project>/board/ - Global learnings:
.agendum/learnings/ - Memory:
.agendum/memory/
Conventions
- MCP tools:
pm_<name>(e.g.,pm_add,pm_next,pm_done) - Store methods: lowercase verb (
create_item,get_item,list_items) - Tests:
test_<module>.py - MCP tools return error strings, never raise exceptions
- No Co-Authored-By lines in commits
- Line length: 120 chars
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.
- 2d ago First seen · 85 lines · 761 tokens per session scan A 8148e509c616
agendum CLAUDE.md is an instructions file published in the GitHub repository sralli/agendum (6 stars, last pushed 4mo ago), licensed MIT. It adds 761 tokens to every session, about $0.0038 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
mcp-redmineApi CLAUDE.md
Claude Code instructions for NeveuGregor/mcp-redmineApi, covering claude.md, repository overview, development environment, python project setup and common development commands.
agents
Always-loaded project anchor. Read this first. Contains project identity, non-negotiables, commands, and pointer to .mex/ROUTER.md for full context. Use GitNexus MCP tools for all structural and impact analysis.
agents
Always-loaded project anchor. Read this first. Contains project identity, non-negotiables, commands, and pointer to ROUTER.md for full context.
WorkGraph AGENTS.md
AGENTS.md instructions for AlexWangzhixin/WorkGraph, a project described as: Local-first drill-down work map and queryable knowledge graph with read-only MCP and optional Obsidian integration.
mcp-archimate AGENTS.md
AGENTS.md instructions for byrondelgado/mcp-archimate, covering agents.md, instruction precedence, canonical instructions, backlog rule and codex translation rules.
huly-mcp CLAUDE.md
Claude Code instructions for dugynoo/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.