eval

A command that compares the current goal with the active reasoning strategies and recommends the best match. A reasoning strategy is a set of instructions for approaching a type of problem.

In plain words
What is it for?
It helps inspect active strategies, rank up to three recommendations, explain the match, and offer the top choice for use.
Why use it?
It helps choose a suitable way to think through a task instead of applying a strategy that does not fit.

Command for Claude Code

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 commands/superuser-pal/awesome-second-brain/eval
Clone the repo
git clone --depth 1 https://github.com/superuser-pal/awesome-second-brain

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00021 $0.00387
Opus 5 $0.00010 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 2d ago against content hash 1c0705153016, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval 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 2d 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/commands/thinking/eval.md · 33 lines

What it actually says

Evaluate which active reasoning strategy is the best fit for the user's current task.

Steps

  1. Ask (if not already stated): "What are you trying to accomplish in this session?" Get a one-sentence description of the task or goal.

  2. Scan active strategies: Read all .md files in docs/strategies/ (exclude INDEX.md), filter to those with status: active in frontmatter. For each, read:

    • description frontmatter field
    • ## When to apply section body
  3. Match: For each active strategy, assess fit against the user's goal. Use the "When to apply" section as the matching criterion.

  4. Recommend: Present a ranked list (best first, max 3) in this format:

    1. /thinking:<slug> — <strategy description> — Why: <one sentence fit rationale>
    2. …
    

    If no active strategy fits well, say so and suggest the user promote one via the strategy skill.

  5. Offer to inject: After presenting the list, ask: "Run /thinking:<slug> to inject the top recommendation, or pick another from the list."

Rules

  • Active only: Only include strategies with status: active in frontmatter. Never reference dormant strategies in the recommendation.
  • No auto-injection: Do not apply any strategy without an explicit /thinking:<slug> invocation.
  • Strict matching: If the ## When to apply section doesn't clearly match the user's goal, do not recommend it.

Related: [[docs/strategies/INDEX|Strategies Index]] · [[CLAUDE]]

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. 2d ago First seen · 33 lines · 21 tokens per session scan A 1c0705153016

Subscribe to this mod's changes

eval is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 387 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.

Related

Other commands, from other repositories

canvas

AI-orchestrated visual canvas production — create, populate, layout, present, generate, and export Obsidian canvases.

AgriciDaniel/claude-canvas · 25 tokens

ingest

Ingest a source (URL/file/text) into Raw Sources + compile 1015 Wiki pages, with mandatory user-purpose gate and mothership cross-linking.

johnfkoo951/cmds-llm-wiki · 33 tokens

audit

Audit the whole Wiki vault against 3 knowledge-integrity criteria — eligibility coverage, MOC-cluster consistency, confidence calibration. Produces a vault health report and queues high-priority pages for /verify.

johnfkoo951/cmds-llm-wiki · 41 tokens

verify

Verify a single Wiki page against 3 knowledge-integrity criteria — eligibility, consistency, confirmability. Writes verificationStatus back to the page; flags conflicts as disputed rather than deleting them.

johnfkoo951/cmds-llm-wiki · 37 tokens

lint

Run comprehensive wiki health check — orphans, broken links, contradictions, stale pages, index sync, MOC coverage, v2/v4/v5 frontmatter coverage, Core Context freshness, and cross-vault link integrity (mainVaultRelated/mainVaultCmds).

johnfkoo951/cmds-llm-wiki · 53 tokens

onboard

Interview-based first-run setup for this LLM Wiki kit. Asks the essential questions (vault location/name, Mode A/B, mothership path, Core Context identity + reuse axes), then fills every placeholder and writes Core Context so the wiki knows you from day one. Activate when the user says "온보딩해줘", "처음 시작할게", "처음 시작"…

johnfkoo951/cmds-llm-wiki · 139 tokens