Borrowing it
Nothing to install: this file belongs to alfonsograziano/auto-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfonsograziano/auto-agent/master/.claude/skills/accuracy-chart/SKILL.mdgit clone --depth 1 https://github.com/alfonsograziano/auto-agentWrote 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.
[](https://agentmods.dev/skills/alfonsograziano/auto-agent/accuracy-chart)<a href="https://agentmods.dev/skills/alfonsograziano/auto-agent/accuracy-chart"><img src="https://agentmods.dev/badge/skills/alfonsograziano/auto-agent/accuracy-chart.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.01920 |
| Opus 5 | $0.00055 | $0.00960 |
| Sonnet 5 | $0.00022 | $0.00384 |
| Haiku 4.5 | $0.00011 | $0.00192 |
Grade A, and why
accuracy-chart 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accuracy Chart Generator
Generate a standalone HTML file with a line chart showing accuracy progression across iterations, plus a summary table, for an auto-agent job.
Data Sources
All data lives inside the job folder. Read these files:
-
out.log.txt— Contains the iteration summary block near the end of the file. Look for the last occurrence of the pattern:Iteration Summary: # Hypothesis Decision Accuracy Duration ──────────────────────────────────────────────────────── 1 001-abc123 CONTINUE 33.3% 4m 25s ... Total time: 16m 18s Final branch: agent-1-hyp-004-12f9ffParse each row for: iteration number, hypothesis ID, decision, accuracy percentage, and duration. Also extract total time and final branch.
-
hypotheses/000-baseline/REPORT.md— Contains the baseline accuracy in a metrics table:| accuracy | 18.3% |Extract the accuracy value. This is the first data point on the chart (x=Baseline).
How to Build the Chart
Step 1: Collect data
- Read
out.log.txtand find the last "Iteration Summary" block (the file may contain multiple job runs appended together). - Read baseline accuracy from the REPORT.md metrics table.
- Build the data series:
[baseline, iter1, iter2, ..., iterN]with accuracy percentages.
Step 2: Compute SVG coordinates
The chart is a hand-crafted SVG (no external libraries). Use these parameters:
- Chart area: x from 72 to
72 + chartWidth, y from 40 to 340 (300px tall) - chartWidth: scale based on number of data points —
Math.max(528, (points - 1) * 63)keeps spacing comfortable - SVG width: chartArea right edge + 40px padding
- X positions: evenly spaced from left edge to right edge
- Y mapping:
y = 340 - (accuracy / 100) * 300
For Y-axis grid lines, use 0%, 20%, 40%, 60%, 80%, 100% as labels.
Step 3: Handle label placement
When consecutive data points have similar accuracy values (within ~8pp), alternate label positions above and below the dots to prevent overlap. Place the percentage label 10px above the dot by default; for alternating ones, place 22px below.
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.
- 8d ago First seen · 131 lines · 109 tokens per session scan A 17f923d13cc9
accuracy-chart is a skill published in the GitHub repository alfonsograziano/auto-agent (56 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 1,920 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…