promote-memory

promote-memory is a skill for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 0 tokens per session (2,575 once invoked), scanned A, original, MIT.

A review process for deciding which lessons from Claude Code’s local project memory should be shared in the project’s main memory file. Five checks vote on each lesson’s usefulness, freshness, duplication, evidence, and format.

In plain words
What is it for?
Use it during monthly memory cleanup, before sharing a project template, or after a major project to review and promote general lessons.
Why use it?
It separates broadly useful knowledge from personal or machine-specific notes, reducing clutter and preventing unsuitable lessons from being shared.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "Does the entry follow the schema in [`.claude/rules/meta-governance.md`](../../rules/meta-governance.md): `[LEARN:category] wrong → right` for corrections, str.

Good fit Use it during monthly memory cleanup, before sharing a project template, or after a major project to review and promote general lessons.

Compare 6 skills from other repositories ↓
About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,566 stars · on GitHub · psantanna.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow
agentmods
npx agentmods add skills/pedrohcgs/claude-code-my-workflow/promote-memory

Made for: Claude Code.

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 promote-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/promote-memory.svg)](https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/promote-memory)
Your own site
<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/promote-memory"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/promote-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Output Handling · line 23
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
How audits are shown
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 5.1 $0.00000 $0.02575
Opus 5 $0.00000 $0.01288
Sonnet 5 $0.00000 $0.00515
Haiku 4.5 $0.00000 $0.00258

Measured 8d ago against content hash f51b2fe7ae29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

promote-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 8d 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.

.claude/skills/promote-memory/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/promote-memory — five-critic council for memory promotion

The template's meta-governance.md rule splits memory into two tiers:

  • MEMORY.md (committed, ≤ 200 lines) — generic learnings that help all forkers.
  • native auto memory (~/.claude/projects/<project>/memory/ — machine-local, typed user/feedback/project/reference, no size cap on topic files) — machine-specific and user-specific learnings.

The rule says generic patterns should sync via git; personal patterns stay local. What it doesn't say is who decides which is which. /promote-memory operationalizes the call: spawn five critics in parallel, each reviewing the candidate [LEARN] entries on a single dimension, and promote on majority vote (3+ of 5).

When to use

  • Monthly memory maintenance. Personal-memory accumulates faster than MEMORY.md; the council periodically harvests the genuinely generic learnings.
  • Before sharing a fork. Someone is about to clone your template — what should they inherit?
  • After a large project ships. Lessons from a paper or a course cycle deserve curation before the next project starts adding noise.
  • As a /loop task. Wire /loop monthly /promote-memory all if you want automated proposal cadence (still requires user approval for each promotion).

When NOT to use

  • For a single fresh [LEARN] after a single correction. Just let auto memory record it; let it sit until the next council runs.
  • For deleting stale entries. Use /learn --revoke or manual edit. /promote-memory only promotes; it doesn't demote.
  • For project-specific context. That belongs in CLAUDE.md or session logs, not in either memory tier.

Read the full file on GitHub · 178 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. 8d ago First seen · 178 lines · 0 tokens per session scan A f51b2fe7ae29

Subscribe to this mod's changes

promote-memory is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,566 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,575 tokens. 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.