analyzer

An analysis step for comparing two coding-agent skills without revealing which one produced each result. It examines the evidence and explains what made one result better.

In plain words
What is it for?
Use it to review A/B tests, compare instructions and tool use, identify errors and recovery patterns, and write recommended skill changes.
Why use it?
It helps turn comparison results into specific improvements instead of relying on guesses or copying a single output.

Agent

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 agents/aipoch/open-science/analyzer
Clone the repo
git clone --depth 1 https://github.com/aipoch/open-science
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 191 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 $0.00000 $0.00191
Opus 5 $0.00000 $0.00096
Sonnet 5 $0.00000 $0.00038
Haiku 4.5 $0.00000 $0.00019

Measured 2d ago against content hash 545e189751b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

resources/skills/skill-creator/agents/analyzer.md · 19 lines

What it actually says

Post-hoc Analyzer Agent

After a valid blind comparison, unblind the result and explain why the winner performed better. Turn the evidence into generalizable Skill improvements rather than copying one output.

Process

  1. Read comparison.json and the A/B mapping.
  2. Read both Skill snapshots and their referenced resources.
  3. Compare transcripts: instruction following, tool usage, errors, recovery, and unnecessary work.
  4. Identify winner strengths and loser weaknesses that plausibly caused the observed difference.
  5. Separate causal evidence from incidental differences.
  6. Propose prioritized changes to instructions, scripts, examples, or edge-case handling.
  7. Write analysis.json using the schema in ../references/schemas.md.

For benchmark-only analysis, look for non-discriminating expectations, high-variance cases, configuration failures, and quality/time/token trade-offs. Do not make subjective quality claims that are unsupported by outputs or human feedback.

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 · 19 lines · 0 tokens per session scan A 545e189751b7

Subscribe to this mod's changes

analyzer is an agent published in the GitHub repository aipoch/open-science (3,307 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 191 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.

Related

Other agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

grounded-review-writer

Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.

gaotiexinqu/OneResearchClaw · 22 tokens

tauri-security-reviewer

Use when reviewing changes that touch the sandbox boundary or credential handling — pathguard.rs, workspacepermissions.rs, securestorage.rs, fsutils.rs, gitops.rs, sidecar.rs, src-tauri/capabilities/.json, tauri.conf.json — or when adding any Tauri command that takes a caller-supplied path, spawns a process, or reads…

kevinlin/cowork-z · 91 tokens

ipc-contract-auditor

Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…

kevinlin/cowork-z · 105 tokens

domain

Single-context layout: one CONTEXT.md and one docs/adr/ at the repo root.

pumblus/okf-harness · 0 tokens

orbit-task-pilot

Read-only bounded preflight for Orbit task metadata. Proposes canonical contextfiles and orchestration warnings without editing, promotion, dispatch, or implementation.

danieljhkim/orbit · 34 tokens