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 bolnet/attestor --skill attestor-memorygit clone --depth 1 https://github.com/bolnet/attestorWrote 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/bolnet/attestor/attestor-memory)<a href="https://agentmods.dev/skills/bolnet/attestor/attestor-memory"><img src="https://agentmods.dev/badge/skills/bolnet/attestor/attestor-memory.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 5.1 | $0.00049 | $0.06654 |
| Opus 5 | $0.00024 | $0.03327 |
| Sonnet 5 | $0.00010 | $0.01331 |
| Haiku 4.5 | $0.00005 | $0.00665 |
Grade A, and why
attestor-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 7d 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
attestor-memory
What this skill does
Attestor is a shared, tenant-isolated memory store for agent teams. It persists every fact across three storage roles (Postgres for documents, Pinecone for vectors, Neo4j for graph) and serves recall through a deterministic six-step cascade — same query, same ranking, no LLM in the hot path. Every fact carries a bi-temporal validity window so an agent can replay any past belief, and every supersession is auditable to its evidence episode.
When to use it
Use attestor when the agent's job depends on memory that survives:
- Multi-session conversations where the user expects continuity weeks or months later (preferences, ongoing projects, durable identity facts).
- Multi-agent products where many agents — orchestrator, planner, executor, reviewer — share state and must not stomp on each other's writes.
- Regulated chat (healthcare, finance, legal) that needs point-in-time reconstruction: "what did the agent know on date X?" or "show every fact that ever superseded this one."
- Workflows where contradictions must be tracked, not silently overwritten — supersession produces an audit chain instead of mutation.
- Self-hosted deployments where the memory data must stay inside the customer's VPC.
When NOT to use it
- Short-lived single-session context. If the relevant memory dies when the conversation ends, put it in the system prompt. Attestor is overkill.
- Pure document retrieval. If you need to chunk and rerank a corpus of PDFs, use a dedicated RAG framework or
file_search. Attestor is for facts, not passages. - An LLM agent runtime. Attestor is the memory backend; the orchestration loop is the caller's responsibility.
- Inline tool use that doesn't need persistence. Direct tool definitions are simpler.
How to install
1. Install the Python package
pip install attestor
The wheel ships with this SKILL.md so any 2026 agent SDK that scans for skills will discover attestor-memory automatically.
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.
- 7d ago First seen · 512 lines · 49 tokens per session scan A 30649ff13951
attestor-memory is a skill published in the GitHub repository bolnet/attestor (14 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 6,654 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
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.