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 Mininglamp-OSS/octo-spec --skill octo-codegit clone --depth 1 https://github.com/Mininglamp-OSS/octo-specWrote 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/mininglamp-oss/octo-spec/octo-code)<a href="https://agentmods.dev/skills/mininglamp-oss/octo-spec/octo-code"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-spec/octo-code/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/mininglamp-oss/octo-spec/octo-code"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-spec/octo-code.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 | $0.00118 | $0.02172 |
| Opus 5 | $0.00059 | $0.01086 |
| Sonnet 5 | $0.00024 | $0.00434 |
| Haiku 4.5 | $0.00012 | $0.00217 |
Grade B, and why
octo-code scanned grade B with 1 finding 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 10d 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.
1. **Engine auth** — `ANTHROPIC_*` in `~/.claude/settings.json` `env` (native + How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
octo-code
Turn an octo chat coding request into a reviewed PR, end to end, without the user
opening Claude Code. The engine is Claude Code headless mode (claude -p);
the standard being followed is octo-spec (the repo this skill ships in).
Layering. This is an integration adapter, not part of octo-spec core. octo-spec stays spec-only (sync / lint / learning-reflow, no runtime engine). This skill only orchestrates: it routes intent, launches the external engine, and checks completion. The 4-phase reasoning is the engine's job.
Shared procedures (preflight, engine call, completion check, onboarding,
cleanup) live in ../shared/octo-code-core.md — read it; this file is the
entry flow that sequences those pieces.
Install & setup (one message, then a doctor)
A team member installs octo-code by sending the bot one message
("install octo-code" / "安装 octo-code"). Be honest about the two halves
(shared/octo-code-core.md §F):
- Skill files install in one message — they are just files; the bot fetches
integrations/octo/skills/octo-code/+shared/into its skills dir and auto-discovery picks them up. - The host engine cannot be installed by a chat message.
claude -pneeds theclaudeCLI installed + non-interactively authenticated, plusgit/gh/jqon the bot host. So right after install, run the doctor and report the gaps instead of pretending the environment is ready:
The doctor is read-only and exits<skill-dir>/shared/octo-code-doctor.sh # human ✅/⚠️/❌ report <skill-dir>/shared/octo-code-doctor.sh --json # machine-readable <skill-dir>/shared/octo-code-doctor.sh --repo <p> # + repo onboarding check0only when every required precondition passes. Relay its output back to the thread so the operator sees exactly what host setup remains. When it is all-green, the user can just say "use octo-code to add X to repo Y".
When to use
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.
- 10d ago First seen · 157 lines · 118 tokens per session scan B c12f494eaf6b
octo-code is a skill published in the GitHub repository Mininglamp-OSS/octo-spec (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 2,172 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.