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 Nako0/devglobe-extension --skill codex-plugingit clone --depth 1 https://github.com/Nako0/devglobe-extensionWrote 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/nako0/devglobe-extension/codex-plugin)<a href="https://agentmods.dev/skills/nako0/devglobe-extension/codex-plugin"><img src="https://agentmods.dev/badge/skills/nako0/devglobe-extension/codex-plugin/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/nako0/devglobe-extension/codex-plugin"><img src="https://agentmods.dev/badge/skills/nako0/devglobe-extension/codex-plugin.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 | $0.00045 | $0.00627 |
| Opus 5.5 | $0.00018 | $0.00251 |
| Sonnet 5.5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade C, and why
devglobe scanned grade C with 2 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
echo "Feature flag: $(grep codex_hooks ~/.codex/config.toml 2>/dev/null || echo 'NOT SET')" Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
DEVGLOBE_SKILL="$(find ~/.codex/skills -name SKILL.md \( -path '*devglobe*' -o -path '*codex-plugin*' \) 2>/dev/null | head -1 | xargs dirname)" What it actually says
DevGlobe for Codex
Track your coding activity on devglobe.app — an interactive 3D globe showing developers coding in real-time.
Visibility settings (anonymous mode, repo sharing on the live globe, profile mode) are managed on devglobe.app/dashboard/settings.
Before running any command below, locate the installed skill directory:
DEVGLOBE_SKILL="$(find ~/.codex/skills -name SKILL.md \( -path '*devglobe*' -o -path '*codex-plugin*' \) 2>/dev/null | head -1 | xargs dirname)"
Setup
$devglobe setup <API_KEY>
Configure DevGlobe with your API key. Get your key at devglobe.app.
echo '{"api_key":"<API_KEY>"}' | node "$DEVGLOBE_SKILL/dist/setup.js"
This will:
- Save your API key to
~/.devglobe/config.toml(mode0600) - Install Codex hooks at
~/.codex/hooks.jsonfor automatic heartbeats - Enable the
codex_hooksfeature flag in~/.codex/config.toml
After setup, restart Codex for hooks to take effect.
Status
$devglobe status <MESSAGE>
Set a status message displayed on the globe next to your avatar.
echo '{"message":"<MESSAGE>"}' | node "$DEVGLOBE_SKILL/dist/update-status.js"
The script reads the API key from ~/.devglobe/config.toml directly.
Diagnostics
$devglobe check
Verify the installation is working:
echo "=== DevGlobe Status ==="
echo "Config: $(test -f ~/.devglobe/config.toml && echo OK || echo 'NOT SET')"
echo "API key set: $(awk -F'"' '/^api_key/ {print ($2 != "" ? "yes" : "no")}' ~/.devglobe/config.toml 2>/dev/null || echo 'NOT SET')"
echo "Hooks: $(grep -cE 'devglobe|codex-plugin' ~/.codex/hooks.json 2>/dev/null || echo 0) references in hooks.json"
echo "Feature flag: $(grep codex_hooks ~/.codex/config.toml 2>/dev/null || echo 'NOT SET')"
$devglobe uninstall
Remove DevGlobe hooks from Codex:
echo '{}' | node "$DEVGLOBE_SKILL/dist/uninstall.js"
What ships with it
22 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.
- .gitignore 21 B
- agents/openai.yaml 116 B
- dist/index.js 23 KB runs code
- dist/setup.js 9.5 KB runs code
- dist/uninstall.js 1.4 KB runs code
- dist/update-status.js 8.9 KB runs code
- package-lock.json 15 KB
- package.json 602 B
- README.md 4.2 KB
- references/hooks-template.json 757 B
- scripts/find-node 483 B
- scripts/heartbeat 275 B
- scripts/setup 392 B
- scripts/uninstall 404 B
- scripts/update-status 416 B
- src/hooks.ts 227 B runs code
- src/index.ts 3.8 KB runs code
- src/setup.ts 2.8 KB runs code
- src/types.ts 364 B runs code
- src/uninstall.ts 1.4 KB runs code
- src/update-status.ts 1015 B runs code
- tsconfig.json 351 B
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.
- 1mo ago First seen · 65 lines · 45 tokens per session scan C da261e1f79b3
devglobe is a skill published in the GitHub repository Nako0/devglobe-extension (217 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 627 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).