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.
npx skills add macintog/codex-spine --skill chart-integritygit clone --depth 1 https://github.com/macintog/codex-spineWrote 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/macintog/codex-spine/chart-integrity)<a href="https://agentmods.dev/skills/macintog/codex-spine/chart-integrity"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/chart-integrity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/macintog/codex-spine/chart-integrity"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/chart-integrity.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00435 |
| Opus 5.5 | $0.00026 | $0.00174 |
| Sonnet 5.5 | $0.00013 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
chart-integrity 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 19d 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.
What it actually says
Chart integrity
What survives a capable model is integrity slips and unchecked rendering, not chart-type choice. Check:
- Comparable inputs. Same definition, unit, population, denominator, and window on both sides. Mark or drop a partial current period beside complete ones; never draw it as a decline. Don't connect across missing intervals.
- Magnitude. Show the base with relative change ("100 → 110, +10%"). Label percentage points vs percent. Length encodings start at zero; a non-zero line axis is fine when disclosed.
- Claims. Titles state only what the data supports; no causal verbs for observational data. Name the interval type when showing uncertainty; don't rank estimates whose intervals make the order unstable. Declare top-N, filtered, or excluded subsets.
- Visible by default. Units, active filters, source and as-of date, and material caveats sit on or beside the chart, not in hover only. Captions and alt text match the active filtered state. KPIs carry a comparator (prior, target, or trend).
- Look at it. Render at delivery size and each viewport you ship. Inspect for clipped or colliding labels, legends over data, illegible ticks, inconsistent panel scales, and color as the only carrier of meaning. Fix and re-render. If you could not render, say so.
A request for "Tufte" or "clean" style means dense, honest evidence: plain background, plain type, direct labels. Skip stock styling (cream paper, serif fonts, a muted red accent) applied for looks.
Use real data; label any synthetic data as synthetic.
For critique, lead with what misleads, then what impairs reading, then craft. Skip items that pass.
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.
- 19d ago First seen · 21 lines · 64 tokens per session scan A 46692101e869
chart-integrity is a skill published in the GitHub repository macintog/codex-spine (12 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 435 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
auto-test-skill
A structured process for critically testing and improving a coding skill. It records test plans, findings, fixes, and quality checks in files that can be reviewed later.
better-prompt
A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
verifier-state-architect
A planning skill for deciding whether an agent skill needs a verifier or a state model. A verifier checks stable facts or safety conditions, while state records progress through an ongoing workflow.
awesome-code
A coordinator for complex software work involving multiple AI agents. It discovers available agents and project rules, then chooses whether the work should use one agent or several in parallel or sequence.
brainstorming
A guided design discussion that uses questions to clarify what should be built before coding starts. It compares possible approaches and removes unnecessary requirements.