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 skills add WenyuChiou/agent-collab-skills --skill agent-shared-memorygit clone --depth 1 https://github.com/WenyuChiou/agent-collab-skillsWrote 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/skills/wenyuchiou/agent-collab-skills/agent-shared-memory)<a href="https://agentmods.dev/skills/wenyuchiou/agent-collab-skills/agent-shared-memory"><img src="https://agentmods.dev/badge/skills/wenyuchiou/agent-collab-skills/agent-shared-memory.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00040 | $0.00785 |
| Opus 5 | $0.00020 | $0.00392 |
| Sonnet 5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
agent-shared-memory 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 5d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-shared-memory
Coordinate durable facts without letting an agent silently rewrite project memory. Read the event schema in references/coord_memory_schema.md before creating or applying a proposal.
Authority
Repository state, current evidence, and recorded human decisions outrank memory. Recall systems are optional caches.
All memory mutations start as proposals:
.coord/memory-proposals/<proposal-id>.json
Without an explicit human approve decision, do not add, supersede, archive, delete, overwrite, or compact canonical memory.
Modes
Read
Read canonical events and return:
- current decisions, following supersedes references
- unresolved questions
- relevant artifact/evidence pointers
- recent execution outcomes
- conflicts or stale claims
Do not load raw agent logs into the primary session. Follow their stable paths only when needed.
Propose
Create a proposal with:
{
"schema_version": 1,
"proposal_id": "<uuid>",
"source_task": "<task id>",
"action": {
"operation": "add | supersede | archive | delete",
"target_ref": null,
"summary": "<compact proposed event>",
"evidence_refs": ["<stable ref>"]
},
"state": "proposed",
"created_at": "<ISO 8601>",
"decision": null
}
Supersede, archive, and delete require a specific action.target_ref. A
proposal with no action.evidence_refs remains pending and must not be applied.
The action object is immutable. Its canonical JSON bytes, not the mutable
proposal envelope, are the approval payload.
Decide
Only a human may approve, decline, or revise a proposal. Record:
- actor
- decision
- timestamp
- rationale
- affected proposal/action hash
- HMAC authorization from the trusted host
Decline and timeout remain non-success. A revise decision creates or updates a proposal; it is not approval.
Apply
Apply only a proposal whose recorded state is approved and whose immutable
action bytes still match decision.affected_action_hash. Decision metadata
and state are outside that hashed payload, so recording approval does not
invalidate the approval hash.
The decision uses the same hmac-sha256 authorization boundary as checkpoint
human records. Do not expose the signing secret to a delegated executor.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · -172 lines · +4 tokens per session 013f73cc1195
- 8d ago First seen · 294 lines · 36 tokens per session scan A ad1e0f6d8ba3
agent-shared-memory is a skill published in the GitHub repository WenyuChiou/agent-collab-skills (26 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 785 once invoked, about $0.0002 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.
Other skills, from other repositories
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Tool-agnostic in design but defaults to a vault at…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
claude-md-updater
Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or add to context.