pce-promotion

pce-promotion is a skill for Claude Code, Codex from CAPHTECH/pce-memory. It costs 56 tokens per session (918 once invoked), scanned A, original, MIT.

A workflow for turning observations or claims into reviewed, lasting project knowledge, with a way to undo a promotion. It covers the steps from initial distillation through approval and rollback.

In plain words
What is it for?
Use it to create promotion candidates from observations, claims, or active context, check memory policy state, record reviewer details, and roll back promoted claims.
Why use it?
It keeps raw observations separate from durable knowledge and records why a candidate was promoted. This makes memory changes reviewable and repairable.

Skill for Claude CodeCodex

Part of the pce-memory-plugin plugin — 4 skills, 1 agent, 3 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/caphtech/pce-memory/pce-promotion
Any agent
npx skills add CAPHTECH/pce-memory --skill pce-promotion
Clone the repo
git clone --depth 1 https://github.com/CAPHTECH/pce-memory

Made for: Claude Code, Codex.

Or install pce-memory-plugin, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for pce-promotion

README.md
[![agentmods](https://agentmods.dev/badge/skills/caphtech/pce-memory/pce-promotion.svg)](https://agentmods.dev/skills/caphtech/pce-memory/pce-promotion)
Your own site
<a href="https://agentmods.dev/skills/caphtech/pce-memory/pce-promotion"><img src="https://agentmods.dev/badge/skills/caphtech/pce-memory/pce-promotion.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.00918
Opus 5 $0.00028 $0.00459
Sonnet 5 $0.00011 $0.00184
Haiku 4.5 $0.00006 $0.00092

Measured 3d ago against content hash c6c93db02393, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pce-promotion 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 3d 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.

pce-memory-plugin/skills/pce-promotion/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PCE Promotion - Distill, Promote, Rollback

Use this skill when the task is specifically about moving knowledge through the v2 promotion pipeline.

Pipeline

observe -> distill -> promote -> rollback

activate and feedback live in pce-core; this skill focuses on the promotion boundary itself.

State Gate

  1. Check pce_memory_state
  2. If Uninitialized, run pce_memory_policy_apply
  3. Continue only after policy state is ready

1. Distill

Create a reviewable promotion candidate from one of these sources:

  • source_observation_ids
  • source_claim_ids
  • active_context_id

Recommended Inputs

{
  "source_observation_ids": ["obs_..."],
  "proposed_kind": "fact",
  "proposed_scope": "project",
  "proposed_memory_type": "knowledge",
  "note": "why this should become durable"
}

Distill Rules

  • Distill is the required abstraction boundary between raw capture and durable memory.
  • Use working_state, knowledge, procedure, or norm for durable intent.
  • Do not propose evidence for durable promotion; it is reserved for micro memory.
  • Candidate output is reviewable and includes invariant checks.
  • promotion_queue is local governance state; it is not a sync surface.

2. Promote

Promote a pending candidate into durable meso or macro memory.

Required Inputs

{
  "candidate_id": "pq_...",
  "provenance": {
    "at": "2026-03-24T00:00:00Z",
    "actor": "claude"
  }
}

Recommended Inputs

  • reviewers: reviewer IDs or names, especially for principle/macro memory
  • review_note: why promotion is justified

Promotion Rules

  • Project scope lands in meso memory.
  • Principle scope lands in macro memory and should carry review lineage.
  • Boundary monotonicity is enforced at promotion time.
  • Secret-bearing candidates cannot silently become durable canonical memory.
  • Promotion returns a rollback_token; keep it in mind when the claim is controversial or newly validated.

3. Rollback

Use rollback when a durable claim is wrong, stale in a harmful way, or superseded.

Read the full file on GitHub · 119 lines

Changes

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.

  1. 3d ago First seen · 119 lines · 56 tokens per session scan A c6c93db02393

Subscribe to this mod's changes

pce-promotion is a skill published in the GitHub repository CAPHTECH/pce-memory (3 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 918 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens