ai-counsel: Skill for Claude Code

.claude/skills/decision-graph-analyzer/SKILL.md

decision-graph-analyzer is a skill for Claude Code from blueman82/ai-counsel. It costs 27 tokens per session (4,736 once invoked), scanned A, original, MIT.

A skill for querying the AI Counsel decision graph, a database of past deliberations and their relationships. It can retrieve similar decisions and inspect the graph's health and statistics.

In plain words
What is it for?
Use it to find similar previous decisions, store completed deliberations, review graph statistics, and check database integrity.
Why use it?
It helps recover relevant past reasoning and investigate whether decision memory is working correctly.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions CLAUDE.md; mentions Codex.

This is blueman82/ai-counsel's own configuration. It tells Claude Code how to work on ai-counsel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-counsel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to blueman82/ai-counsel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/blueman82/ai-counsel/main/.claude/skills/decision-graph-analyzer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/blueman82/ai-counsel

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 decision-graph-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/blueman82/ai-counsel/decision-graph-analyzer.svg)](https://agentmods.dev/skills/blueman82/ai-counsel/decision-graph-analyzer)
Your own site
<a href="https://agentmods.dev/skills/blueman82/ai-counsel/decision-graph-analyzer"><img src="https://agentmods.dev/badge/skills/blueman82/ai-counsel/decision-graph-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,736 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 $0.00027 $0.04736
Opus 5 $0.00014 $0.02368
Sonnet 5 $0.00005 $0.00947
Haiku 4.5 $0.00003 $0.00474

Measured 8d ago against content hash 382fe70c3748, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decision-graph-analyzer 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/decision-graph-analyzer/SKILL.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Graph Analyzer Skill

Overview

The decision graph module (decision_graph/) stores completed deliberations and provides semantic similarity-based retrieval for context injection. This skill teaches you how to query, analyze, and troubleshoot the decision graph effectively.

Core Components

Storage Layer (decision_graph/storage.py)

  • DecisionGraphStorage: SQLite3 backend with CRUD operations
  • Schema: decision_nodes, participant_stances, decision_similarities
  • Indexes: Optimized for timestamp (recency), question (duplicates), similarity (retrieval)
  • Connection: Use :memory: for testing, file path for production

Integration Layer (decision_graph/integration.py)

  • DecisionGraphIntegration: High-level API facade
  • Methods:
    • store_deliberation(question, result): Save completed deliberation
    • get_context_for_deliberation(question): Retrieve similar past decisions
    • get_graph_stats(): Get monitoring statistics
    • health_check(): Validate database integrity

Retrieval Layer (decision_graph/retrieval.py)

  • DecisionRetriever: Finds relevant decisions and formats context
  • Key Features:
    • Two-tier caching (L1: query results, L2: embeddings)
    • Adaptive k (2-5 results based on database size)
    • Noise floor filtering (0.40 minimum similarity)
    • Tiered formatting (strong/moderate/brief)

Maintenance Layer (decision_graph/maintenance.py)

  • DecisionGraphMaintenance: Monitoring and health checks
  • Methods:
    • get_database_stats(): Node/stance/similarity counts, DB size
    • analyze_growth(days): Growth rate and projections
    • health_check(): Validate data integrity
    • estimate_archival_benefit(): Space savings simulation

Common Query Patterns

1. Find Similar Decisions

When: You want to see what past deliberations are related to a new question.

from decision_graph.integration import DecisionGraphIntegration
from decision_graph.storage import DecisionGraphStorage

# Initialize
storage = DecisionGraphStorage("decision_graph.db")
integration = DecisionGraphIntegration(storage)

# Get similar decisions with context
question = "Should we adopt TypeScript for the project?"
context = integration.get_context_for_deliberation(question)

if context:
    print("Found relevant past decisions:")
    print(context)
else:
    print("No similar past decisions found")

Read the full file on GitHub · 560 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 · 560 lines · 27 tokens per session scan A 382fe70c3748

Subscribe to this mod's changes

decision-graph-analyzer is a skill published in the GitHub repository blueman82/ai-counsel (1 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 4,736 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

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

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

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.

GanyuanRan/Aegis · 45 tokens