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 CAPHTECH/pce-memory --skill pce-coregit clone --depth 1 https://github.com/CAPHTECH/pce-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/skills/caphtech/pce-memory/pce-core)<a href="https://agentmods.dev/skills/caphtech/pce-memory/pce-core"><img src="https://agentmods.dev/badge/skills/caphtech/pce-memory/pce-core/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/caphtech/pce-memory/pce-core"><img src="https://agentmods.dev/badge/skills/caphtech/pce-memory/pce-core.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 | $0.00059 | $0.02004 |
| Opus 5.5 | $0.00024 | $0.00802 |
| Sonnet 5.5 | $0.00012 | $0.00401 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
pce-core 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 1mo 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PCE Core - V2 Knowledge Workflow
Manages the v2 pce-memory workflow:
observe -> distill -> promote -> activate(intent) -> feedback -> rollback
pce_memory_upsert still exists, but only as a narrow escape hatch for already-distilled durable knowledge.
Argument Parsing
Parse $ARGUMENTS:
activate [query]→ Intent-aware recall modeobserve [text]→ Raw micro-memory capturedistill [source ids or guidance]→ Promotion candidate creationpromote [candidate-id]→ Durable promotionrollback [claim-id] [reason]→ Durable repair/supersessionupsert [kind] [text]→ Escape hatch for already-distilled durable knowledgefeedback [claim-id] [signal]→ Feedback mode- No arguments → Full workflow guide
State Gate
- Check current state with
pce_memory_state - If
Uninitialized, runpce_memory_policy_apply - Continue only after the policy state is ready for the tool you need
1. Observe (Raw Micro Memory Only)
Use pce_memory_observe for raw inputs:
- session work-in-progress
- chat/tool/file/http/system outputs
- debugging notes and local evidence
- secret or PII-bearing material that must not become durable inline
Rules
- Observe is raw-only. It does not create durable claims inline.
- Do not use legacy inline extraction modes such as
single_claim_v0. extract: { mode: "noop" }is only a compatibility knob and still preserves raw-only behavior.- Use
boundary_class: secretonly in observe, never in upsert. - Use observe instead of upsert for anything session-scoped.
Typical Input
{
"source_type": "chat|tool|file|http|system",
"content": "...",
"boundary_class": "public|internal|pii|secret",
"tags": ["..."],
"ttl_days": 7
}
2. Distill (Create Promotion Candidate)
Use pce_memory_distill to convert observations, claims, or an active context into a reviewable candidate.
Inputs
source_observation_ids: Raw observations to abstractsource_claim_ids: Existing durable claims to refine or supersedeactive_context_id: Promote from a planned working setproposed_kind:fact | preference | task | policy_hintproposed_scope:project | principleproposed_memory_type:working_state | knowledge | procedure | normnote: Distillation hint for reviewers
What ships with it
2 files 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.
- 1mo ago First seen · 232 lines · 59 tokens per session scan A eeab6f09867d
pce-core is a skill published in the GitHub repository CAPHTECH/pce-memory (3 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 2,004 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.