octo-server: Skill for Claude Code

.claude/skills/octospec-workflow/SKILL.md

octospec-workflow is a skill for Claude Code from Mininglamp-OSS/octo-server. It costs 135 tokens per session (901 once invoked), scanned A, original, Apache-2.0.

A workflow for making substantial code changes through four stages: planning, implementation, verification, and finishing. It uses task briefs and repository rules to guide the work.

In plain words
What is it for?
Use it for features, bug fixes, refactors, and API changes that affect important behavior. Small documentation, typo, lint, configuration, or dependency changes do not require it.
Why use it?
It gives non-trivial changes a written scope, checks them against project requirements, and records the result before a pull request is opened.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is Mininglamp-OSS/octo-server's own configuration. It tells Claude Code how to work on octo-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything octo-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Mininglamp-OSS/octo-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Mininglamp-OSS/octo-server/main/.claude/skills/octospec-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Mininglamp-OSS/octo-server

Made for: Claude Code.

Wrote 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.

agentmods badge for octospec-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/mininglamp-oss/octo-server/octospec-workflow/github.svg)](https://agentmods.dev/skills/mininglamp-oss/octo-server/octospec-workflow)
Your own site
<a href="https://agentmods.dev/skills/mininglamp-oss/octo-server/octospec-workflow"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-server/octospec-workflow/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.

agentmods 80×15 button for octospec-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/mininglamp-oss/octo-server/octospec-workflow"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-server/octospec-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00135 $0.00901
Opus 5 $0.00068 $0.00451
Sonnet 5 $0.00027 $0.00180
Haiku 4.5 $0.00014 $0.00090

Measured 11d ago against content hash 9b161235508a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

octospec-workflow 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 11d 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.

.claude/skills/octospec-workflow/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

octospec workflow

This repository uses the octospec engineering standard. When you are asked to make a non-trivial code change here, run the 4-phase flow instead of editing code directly. Rules live in .octospec/ and are the source of truth for this repo's conventions.

When to run this

Run the flow for: a new feature, a bug fix, a refactor, an API change, or any change that touches load-bearing behavior.

Do NOT run the flow for trivial changes: a typo, a docs-only edit, a lint-only fix, a pure config or dependency bump. Just make those directly.

The 4 phases

Run them in order. Each phase maps to a slash command the user can also invoke manually; as a skill you perform the same steps.

1. Plan

  • Choose a short kebab-case <slug>.
  • Read .octospec/tasks/_brief.template.md.
  • Inspect the relevant existing code, then write .octospec/tasks/<slug>/brief.md with: Goal, Load-bearing list (use the same tags as .octospec/rules/_index.yaml inject_when.touches where they apply), Out of scope, Acceptance.
  • Show the brief and get confirmation before writing code.

2. Implement

  • Resolve applicable rules: read .octospec/rules/_index.yaml and .octospec/_global/ (if synced). A rule applies when its inject_when.paths glob matches a file you will touch, OR its inject_when.touches tag is in the brief's load-bearing list. A repo-tier rule overrides a global one with the same id.
  • Read the full text of each matching rule and follow it. Prioritize load_bearing: true rules.
  • Record what you used in .octospec/tasks/<slug>/context.yaml.
  • Write the code. Do not commit yet.

3. Verify

  • Review the diff against each injected rule (trace load-bearing paths, not just the happy path).
  • Confirm the diff meets the brief's Acceptance and did not touch anything in Out of scope.
  • Run this repo's gates (lint / type-check / tests; see CLAUDE.md / AGENTS.md).
  • Self-fix what you can.

4. Finish

  • Run the final gate once more.
  • Write .octospec/journal/shared/<slug>.md (what was done + any learning). Start it with OKF frontmatter (type: Journal + title/description/tags/ timestamp) and add a dated entry to .octospec/log.md.
  • If a learning is worth reusing, stage it in .octospec/learnings/pending/ (promotion into rules/ is a separate reviewed PR — do not auto-edit rules).
  • Open a PR. Fill the PR template's Linked Spec (→ the brief) and the COMPREHENSION three questions to substance, for load-bearing / architectural / P0 changes.

Read the full file on GitHub · 79 lines

Changes

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.

  1. 11d ago First seen · 79 lines · 135 tokens per session scan A 9b161235508a

Subscribe to this mod's changes

octospec-workflow is a skill published in the GitHub repository Mininglamp-OSS/octo-server (925 stars, last pushed today), licensed Apache-2.0. It adds 135 tokens to every session and 901 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

vs-chat

Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.

volcengine/SearchCLI · 22 tokens

code-guidelines-go

Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…

dimetron/pi-go · 124 tokens

go-127

What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…

dimetron/pi-go · 177 tokens

email-evals

Author and safely run deterministic email-agent evaluation suites with dedicated e2a test agents. Use when a user wants to define synthetic email cases, validate a suite, inspect its dry-run plan, run it after approval, or regrade changed assertions.

tokencanopy/e2a · 53 tokens

bubbletea-testing

Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…

dimetron/pi-go · 139 tokens

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens