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 Chemaclass/agnostic-ai --skill shared-memorygit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/shared-memory)<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/shared-memory"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/shared-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/shared-memory"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/shared-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00593 |
| Opus 5.5 | $0.00006 | $0.00237 |
| Sonnet 5.5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
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 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shared-memory
Recall or curate the shared project memory when the user asks. Choose the mode from the request: "what do we know about X" recalls; "clean up memory" curates. The shared-memory-policy rule covers when and how to save a fact.
Project memory is .agnostic-ai/memory/ and personal memory is .agnostic-ai/local/memory/, both in the current project root, including when this skill is installed globally. For root lookup, use canonical paths for the current directory, candidate ancestors, and the effective global source root (AGNOSTIC_AI_HOME when nonempty, otherwise ~/.agnostic-ai). Find the nearest ancestor containing agnostic-ai.yaml or the legacy agnostic.config.yaml, but exclude the effective global source root: its home config never identifies a project. The remaining nearest configured ancestor is the project root. If none exists, use git rev-parse --show-toplevel for the current checkout. When the project's agnostic-ai.local.yaml sets memory.personal: repo, personal memory is instead one folder per repository under <global source root>/local/memory/, named after the repository and shared by its worktrees; use the one your session context names, or the one agnostic-ai memory path prints when none does.
Each folder holds MEMORY.md, an index with one - [Title](<slug>.md): <hook> line per fact, and one topic file per fact. A topic file has frontmatter name, description, and metadata.type (user, feedback, project, or reference), then the fact, a **Why:** line, and a **How to apply:** line.
Recall
- Read both
MEMORY.mdindexes. If neither exists, tell the user the project has no shared memory yet. - Pick the index lines that match the request and read their topic files.
- Before you report a fact that names a file, flag, or command, check that it still exists. Report a stale fact as stale.
Curate
- Read each index and every topic file. Curate each folder on its own, and move a fact between them only when the user asks.
- Find duplicates to merge, facts the code or rules now state, facts that name something that no longer exists, topic files missing from the index, and index lines whose file is missing. Keep the index under 100 lines.
- Show one diff per changed file and wait for the user to confirm. Apply only what they approve.
- Never write secrets, and never write any tool's own memory store. To bring facts over from one, run
agnostic-ai memory import.
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 Changed b1eb8d11316c
- 8d ago Changed 175a3cc9c050
- 9d ago First seen · 26 lines · 16 tokens per session scan A 47a1d684f8fe
shared-memory is a skill published in the GitHub repository Chemaclass/agnostic-ai (25 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 593 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
session-end
Close a session — summarize changes, suggest commits, write a journal entry (episodic trace), write fresh NEXT.md (handoff). Chains to dream for substantive sessions.
dream
Sleep-consolidation pass — replay journal entries to distill them into garden/essential/USER.md, garden/essential/SOUL.md, garden/ .md, and new procedures in forge/ (all T1 autonomous within capacity). Propose T2 graduations to 3-control/foundation/SOUL.md, 3-control/foundation/PRINCIPLE.md, and 3-control/rule/ for…
session-start
Load read order into agent context at every session begin. Invoke detect-runtime in drift-check mode and propose re-ratify on runtime mismatch with profile.md. Consume + clear NEXT.md (the working buffer). Brief Owner on state. Not the one-time bootstrap (use init for that).
tldr-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into TLDR format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /tldr-compress FILEPATH or "compress…
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.