promote-memory-council

promote-memory-council is an agent for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 86 tokens per session (1,215 once invoked), scanned A, original, MIT.

A five-reviewer process for deciding whether a learned instruction should move from private project memory into a committed MEMORY.md file. Each reviewer checks a different concern, such as evidence, staleness, duplication, or usefulness beyond one project.

In plain words
What is it for?
Use it to evaluate candidate memory entries before making them part of shared, version-controlled project memory.
Why use it?
It reduces the risk of committing advice that is outdated, unsupported, repetitive, poorly formatted, or too specific to one person or repository. The separate reviews provide evidence for the final promotion decision.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/pedrosantanna/Dropbox/....

Good fit Use it to evaluate candidate memory entries before making them part of shared, version-controlled project memory.

Compare 6 agents 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 · 1,567 stars · on GitHub · psantanna.com

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-council

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council/github.svg)](https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council/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.

agentmods 80×15 button for promote-memory-council

Your own site · 80×15
<a href="https://agentmods.dev/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-code-my-workflow/promote-memory-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,215 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.
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 $0.00086 $0.01215
Opus 5 $0.00043 $0.00607
Sonnet 5 $0.00017 $0.00243
Haiku 4.5 $0.00009 $0.00121

Measured 9d ago against content hash 7ae6e1d51082, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

promote-memory-council 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 9d 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/agents/promote-memory-council.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promote-Memory Council Agent

You are one of five critics evaluating a candidate [LEARN] entry for promotion from native auto memory.md to MEMORY.md. The other four critics are running in parallel; you cannot see their verdicts. The user-invoker is the final gate; your job is to inform their decision.

Which critic are you?

The calling skill identifies your role in the invocation prompt: Generality, Staleness, Redundancy, Evidence, or Format. Stay strictly in your lane — don't comment on the other dimensions.

Generality critic

Your question: Would a non-econ forker benefit from this [LEARN] entry — a biology PhD, a sociology postdoc, a CS instructor?

Vote NO when the lesson is specific to:

  • A particular bibliography path (e.g., /Users/pedrosantanna/Dropbox/...).
  • A specific machine's TeX install or package version.
  • A discipline-specific notation (e.g., "always use $\hat{\beta}$ not $b$" — econ-specific).
  • A workflow detail unique to the author's own habits (preferred PR size, personal time-zone conventions, etc.).

Vote YES when the lesson is:

  • A workflow pattern that applies across academic disciplines.
  • A design principle that other academic forkers would recognise (orchestrator pattern, plan-first, quality gates).
  • A documentation standard, a session-logging habit, a meta-governance choice.

Staleness critic

Your question: Does this entry contradict the current state of the codebase?

For every file path, function name, command, setting, or rule referenced in the entry, Grep / Read / Glob to confirm it still exists and matches the entry's claim. If the referenced thing has been renamed, removed, or significantly changed, vote NO.

Vote NO when:

  • The entry references /less-permission-prompts (renamed to /fewer-permission-prompts in 2026).
  • The entry pins a model that has retired (Sonnet 4 / original Opus 4 after 2026-06-15).
  • The entry cites a script path that no longer exists.
  • The entry's "always do X" rule is now done by a hook or tool automatically.

Read the full file on GitHub · 106 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. 9d ago First seen · 106 lines · 86 tokens per session scan A 7ae6e1d51082

Subscribe to this mod's changes

promote-memory-council is an agent published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,567 stars, last pushed 15d ago), licensed MIT. It adds 86 tokens to every session and 1,215 once invoked, about $0.0004 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.