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/zenetusken/consolidate-memory/agents-mdgit clone --depth 1 https://github.com/Zenetusken/consolidate-memoryWrote 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/zenetusken/consolidate-memory/agents-md)<a href="https://agentmods.dev/instructions/zenetusken/consolidate-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/zenetusken/consolidate-memory/agents-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 | $0.04762 | $0.04762 |
| Opus 5 | $0.02381 | $0.02381 |
| Sonnet 5 | $0.00952 | $0.00952 |
| Haiku 4.5 | $0.00476 | $0.00476 |
Grade A, and why
consolidate-memory AGENTS.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 today.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — consolidate-memory
Agent operating manual for this repo, authored from a 5-agent codebase map and
verified against the live tree at v0.4.7 (2026-09-03). CLAUDE.md holds the
same conventions with more narrative; where they disagree, the live files win.
Under the plugin's own tier model this file is an on-demand store — read it when
you work here; the always-loaded store is CLAUDE.md + the auto-memory
MEMORY.md index.
What this is
A Claude Code plugin: cross-project, verification-first memory for agents — the layer beyond Claude Code's built-in per-project Auto Dream, adding a governed cross-project store plus verification against the live code. This repo is both the plugin and its marketplace. Two plugins ship from it:
| Plugin | Version | Role |
|---|---|---|
consolidate-memory |
0.4.7 | The product: a 6-phase dream workflow, StoreContext-resolved native stores, operator-enrolled domain isolation, SQLite control plane + journal (sole authority for holders/grants/migration state per ADR 023), sole canonical writer, cm local native writer (local recall-key pointer + extract_wikilinks as pull), facts-manifest beacon/pull cache, paginated journal inventory, tiered context-budget accounting. Unenrolled projects are local-only. |
dream-beta-tester |
0.1.8 | The QA companion: beta-tests the dream skill itself — deterministic invariant oracle + judgment-lens pass + maintainer pre-push gate |
End users install with /plugin marketplace add Zenetusken/consolidate-memory +
/plugin install consolidate-memory@zenetusken-plugins. The marketplace must be
added via Git owner/repo shorthand — never a URL to marketplace.json (its
relative source paths only resolve over Git).
Commands you will actually run
Dev loop — after any change to plugins/consolidate-memory/scripts/:
python3 tests/smoke.py # the zero-dep gate — ~1518 assertions over every script's
# pure functions + the cross-module pins; exit 1 on any failure
python3 tests/simulate_accumulation.py # lifecycle accumulation sim (probes A–W + X–AF) — the
# store-mechanics gate; CI runs it too
mypy --config-file mypy.ini # dev-only TypedDict contract check (mypy is NOT a runtime dep)
./cm status # spot-check Phase-0 output
python3 tests/validate_manifests.py # portable manifest checker (it has NO --strict flag;
# --strict belongs to the claude CLI)
claude plugin validate ./plugins/consolidate-memory --strict # when iterating on the published artifact
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.
- today Changed · +53 lines · +1,113 tokens per session 6a45d792354b
- 4d ago First seen · 229 lines · 3,649 tokens per session scan A d2d78f66c20d
consolidate-memory AGENTS.md is an instructions file published in the GitHub repository Zenetusken/consolidate-memory (6 stars, last pushed today), licensed MIT. It adds 4,762 tokens to every session, about $0.0238 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
SecureContext CLAUDE.md
Instructions for iampantherr/SecureContext, covering securecontext — agent instructions, what this project is, directory layout, build commands and 13 mcp tools.
claude-memory-framework CLAUDE.md
Instructions for guachoxx/claude-memory-framework, covering claude memory index, system overview, configuration, quick navigation and boot sequence.
BorisChernyClaudeMarkdown CLAUDE.md
Claude Code instructions for maximus0411/BorisChernyClaudeMarkdown, covering workflow orchestration, 1. plan mode default, 2. subagent strategy to keep main context window clean, 3. self-improvement loop and 4. verification before done.
claude-neo4j-mem AGENTS.md
AGENTS.md instructions for troglodyte/claude-neo4j-mem, a project described as: Claude Neo4j memory plugin, in the manner of claude-mem.
agent_session_manager CLAUDE.md
Instructions for nshkrdotcom/agent_session_manager, a project described as: Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows.
kraken CLAUDE.md
Instructions for rafael-adcp/kraken: This project has a knowledge graph at graphify-out/ with god nodes, community structure, and cross-file relationships.