evograph

evograph is a skill for Claude Code, Codex from skillberry-ai/cap-evolve. It costs 184 tokens per session (1,218 once invoked), scanned A, original, Apache-2.0.

A deprecated agent-mode algorithm that searched for fixes by assigning one solver agent to each failure group.

In plain words
What is it for?
It remains useful for reading existing evograph run directories and their file-format records.
Why use it?
It should not be used for new runs because its distinctive approach is already covered by another algorithm and had flawed evaluation safeguards.

Skill for Claude CodeCodex

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 skills/skillberry-ai/cap-evolve/evograph
Any agent
npx skills add skillberry-ai/cap-evolve --skill evograph
Clone the repo
git clone --depth 1 https://github.com/skillberry-ai/cap-evolve

Made for: Claude Code, Codex.

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 evograph

README.md
[![agentmods](https://agentmods.dev/badge/skills/skillberry-ai/cap-evolve/evograph.svg)](https://agentmods.dev/skills/skillberry-ai/cap-evolve/evograph)
Your own site
<a href="https://agentmods.dev/skills/skillberry-ai/cap-evolve/evograph"><img src="https://agentmods.dev/badge/skills/skillberry-ai/cap-evolve/evograph.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 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 $0.00184 $0.01218
Opus 5 $0.00092 $0.00609
Sonnet 5 $0.00037 $0.00244
Haiku 4.5 $0.00018 $0.00122

Measured 4d ago against content hash 297cf97e1adb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evograph 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 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/_bootstrap.py, scripts/abstract.py, scripts/check.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/algorithms/evograph/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

evograph — DEPRECATED

Do not select algorithm_skill: evograph for a new run. Use agent-optimize (agent mode) or hill-climb / gepa / skillopt (deterministic). This file stays so an existing evograph run dir is still readable and so the wiki file-format contract has an owner until it moves.

Why it is deprecated

evograph advertised one distinctive capability — a collaborative weakness graph with one solver agent per weakness, merged into a shared candidate each round. Measured against its four siblings, that capability is not distinctive and the part that was distinctive was a defect:

  • The fan-out already exists, gated properly. agent-optimize fans out N sibling candidates from the same parent, one diagnosed failure cluster each, every sibling in its own working copy (a git worktree when the capability is in git), gated one at a time with a re-gate after each accept so several fixes accumulate into one lineage honestly. That is evograph's round, minus the flaws below. The clustering itself is phases/diagnose's job in both cases.
  • Acceptance was never held out. evograph kept a merge on a raw delta over a frozen 3-task subset of train, self-reported by the solver subagent that made the edit — no val split, no standard error, no Δ > k·SE. Between baseline and finalize an evograph run took no held-out measurement at all, so the sealed test number was the first honest signal anyone saw. Whole-round revert existed only as a one-round-late substitute for the gate it lacked; wire the real gate and there is nothing left for it to catch.
  • What remains unique is an output format, not a search strategy. The run-dir wiki/ is genuinely useful, but the dashboard renders the Weakness-graph tab from wiki/ presence alone, for any algorithm that writes the format (core/cap_evolve/dashboard.py). An output contract does not earn a second agent-mode algorithm that users must choose between.

There is no deterministic engine

Read the full file on GitHub · 83 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 83 lines · 184 tokens per session scan A 297cf97e1adb

Subscribe to this mod's changes

evograph is a skill published in the GitHub repository skillberry-ai/cap-evolve (47 stars, last pushed 4d ago), licensed Apache-2.0. It adds 184 tokens to every session and 1,218 once invoked, about $0.0009 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.