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 sasly2048/codex-atlas --skill insightsgit clone --depth 1 https://github.com/sasly2048/codex-atlasWrote 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/sasly2048/codex-atlas/insights)<a href="https://agentmods.dev/skills/sasly2048/codex-atlas/insights"><img src="https://agentmods.dev/badge/skills/sasly2048/codex-atlas/insights/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/sasly2048/codex-atlas/insights"><img src="https://agentmods.dev/badge/skills/sasly2048/codex-atlas/insights.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 | $0.00078 | $0.00511 |
| Opus 5 | $0.00039 | $0.00255 |
| Sonnet 5 | $0.00016 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
insights 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 9d 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
cc-atlas usage insights
cc-atlas is a bundled CLI that reads the user's local ~/.claude/projects
session transcripts (and any git repos they've configured) into a local
SQLite database and computes usage analytics. Nothing leaves the machine —
no API calls, no telemetry.
Workflow
- Run
cc-atlas syncfirst. It's safe and fast to re-run — incremental, only re-parsing transcript files that changed since the last sync. - For a specific question, prefer
cc-atlas ask "<question>". It understands a fixed vocabulary — hours, sessions, error rate, streak, burnout, most-used tool, cost, commits — optionally scoped to a project name and a period (today / this week / this month / all time). It is pattern-matching, not a language model. If it replies "I didn't recognize that one," fall back tocc-atlas export --format jsonand compute the answer yourself from the returned summary rather than guessing. - For a one-line snapshot (streak, hours today, burnout risk), use
cc-atlas status --json. - For a fuller written report, use
cc-atlas report <day|week|month> --format markdown.
What this can't answer directly
Cross-project comparison, session replay, team activity, anomaly
detection, and goal tracking are interactive-only menu screens — they need
a real terminal to select options. If the user wants one of those, tell
them to run cc-atlas directly in their own terminal to open the menu.
Don't try to drive interactive prompts through a tool call.
Be honest about the numbers
- Dollar figures use an illustrative blended rate, not Anthropic's actual per-model pricing — say so if you report a cost.
- If
cc-atlas syncfinds no session data yet, say that plainly rather than presenting a zero as a real answer.
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.
- 9d ago First seen · 44 lines · 78 tokens per session scan A 7e42dced46ac
insights is a skill published in the GitHub repository sasly2048/codex-atlas (1 stars, last pushed 10d ago), licensed MIT. It adds 78 tokens to every session and 511 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
prewalk
Use when the user wants a coding task executed with a strong planner model first and a faster/cheaper executor model after the first successful implementation edit.
cinematic-storyboard-sheet
Generate professional Hollywood-caliber vertical storyboard sheet images from cinematic storyboard text, shot lists, scripts, or character reference images. Use when Codex must call imagegen to create an image-only black-background storyboard layout with 3:2 cinematic frames on the left, aligned production text on the…
deconstruct-bias-dialogue
Guided bias-deconstruction dialogue that combines Madhyamaka catuskoti, phenomenological epoche, Socratic elenchus, and Popperian falsification into progressive questions. Use when the user asks to examine assumptions, biases, beliefs, polarizing claims, identity or group judgments, ethical or political disputes…
pixel-office
Show Codex subagents working in a live Stardew-style pixel office web page. Use PROACTIVELY and implicitly whenever a task starts or observes subagents (spawnagent/collaboration or subagentactivity), even when the user never mentions this plugin; automatically open the Codex app right sidebar page. Also use when the…
manage-taskboard
Manage Codex Taskboard / e-taskboard work with taskctl. Use for taskboard issue IDs, status sync, comments, or taskctl cloud setup—not for unrelated product docs.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.