org-memory-compile

org-memory-compile is a command for Claude Code from allsmog/vuln-scout. It costs 17 tokens per session (566 once invoked), scanned A, original, MIT.

A command that turns repeated human-reviewed security decisions into reusable project guidance. It stores confirmed findings, accepted suppressions, custom scanning rules, and review patterns.

In plain words
What is it for?
Use it to compile reviewed scan history and rule statistics, choose how much identifying information to retain, preview proposed memory, and create project-specific security rules.
Why use it?
Future scans can use the organisation's past decisions instead of repeatedly raising the same accepted issues or missing known patterns.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vuln-scout plugin — 32 skills, 15 commands, 9 agents shipped together

Good fit Use it to compile reviewed scan history and rule statistics, choose how much identifying information to retain, preview proposed memory, and create project-specific security rules.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add allsmog/vuln-scout
Claude Code
/plugin install vuln-scout

Made for: Claude Code.

Or install vuln-scout, the plugin that ships this one along with the rest of its 32 skills, 15 commands, 9 agents.

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 org-memory-compile

README.md
[![agentmods](https://agentmods.dev/badge/commands/allsmog/vuln-scout/org-memory-compile.svg)](https://agentmods.dev/commands/allsmog/vuln-scout/org-memory-compile)
Your own site
<a href="https://agentmods.dev/commands/allsmog/vuln-scout/org-memory-compile"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/org-memory-compile.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00017 $0.00566
Opus 5 $0.00009 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 8d ago against content hash 9554924559f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

org-memory-compile 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.

vuln-scout/commands/org-memory-compile.md · 67 lines

What it actually says

Compile Org Memory

Compile repeated human-reviewed verdicts into .vuln-scout/org-memory/ so future scans can reuse organization-specific suppressions, confirmed patterns, and reviewer heuristics.

Usage

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/org_memory_compiler.py" \
  --project-root . \
  --privacy hashed
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/org_memory_compiler.py" \
  --project-root . \
  --privacy strict \
  --dry-run

Inputs

  • .claude/scan-history/*.json
  • .claude/rule-stats.json
  • .claude/review-ledger.json
  • Human-reviewed findings where verdict is verified or false_positive

Outputs

  • .vuln-scout/org-memory/accepted-suppressions.yaml
  • .vuln-scout/org-memory/confirmed-findings.yaml
  • .vuln-scout/org-memory/custom-rules/semgrep/*.yaml
  • .vuln-scout/org-memory/review-patterns.yaml
  • .vuln-scout/org-memory/manifest.json

Flags

Flag Effect
--privacy open Store paths and excerpts verbatim
--privacy hashed Store SHA-256 hashes for paths and excerpts
--privacy strict Store only rule IDs, verdict counts, and CWE metadata
--dry-run Print proposed memory without writing files
--force Allow overwriting strict memory with open privacy
--allow-commit Do not add .vuln-scout/org-memory/ to .gitignore

Review Policy

Only human-reviewed provenance can graduate into org memory:

  • Confirmed findings require at least 3 verified samples and a verified rate of at least 50%.
  • Accepted suppressions require the same stable key to be manually suppressed at least twice.
  • Demotion hints reuse MIN_SAMPLES_FOR_DEMOTE from feedback_collector.py to avoid single-sample overfit.

By default the compiler adds .vuln-scout/org-memory/ to the target repository .gitignore. Use --allow-commit only when the repository owner has decided the generated memory is safe to commit.

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 · 67 lines · 17 tokens per session scan A 9554924559f4

Subscribe to this mod's changes

org-memory-compile is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 566 once invoked, about $0.0001 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.