A skill for managing specification documents and issues in Sudocode, a system that stores requirements and work items as Markdown files. It also tracks dependencies and implementation feedback.

Use it for Sudocode spec and issue operations, including creating or editing specs, tracking issues, recording feedback, and checking dependencies. It is required when working with Sudocode features or issues.

It keeps requirements, actionable work, and relationships between tasks organized across sessions. This helps connect what a user wants with the work needed to build it.

sudocode — Skill for Claude Code by sudocode-ai

Install

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.

Any agent

npx skills add sudocode-ai/sudocode --skill sudocode

Clone the repo

git clone --depth 1 https://github.com/sudocode-ai/sudocode

Made for: Claude Code.

Or install sudocode, the plugin that ships this one along with the rest of its 1 skill, 12 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sudocode-ai/sudocode/sudocode/github.svg)](https://agentmods.dev/skills/sudocode-ai/sudocode/sudocode)

Your own site

<a href="https://agentmods.dev/skills/sudocode-ai/sudocode/sudocode"><img src="https://agentmods.dev/badge/skills/sudocode-ai/sudocode/sudocode/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sudocode-ai/sudocode/sudocode"><img src="https://agentmods.dev/badge/skills/sudocode-ai/sudocode/sudocode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,104 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00118	$0.02104
Opus 5.5	$0.00047	$0.00842
Sonnet 5.5	$0.00024	$0.00421
Haiku 4.5	$0.00012	$0.00210

Measured 2mo ago against content hash 29a02f966049, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sudocode 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 2mo 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.

skills/sudocode/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sudocode: Spec & Issue Management

Spec-driven development and issue management system. Work persists across sessions, specs guide implementation, dependency graphs ensure correct execution order, feedback loops close requirements gaps.

Core Concepts

Specs: Requirements/design documents (markdown in .sudocode/specs/) - user-initiated, capture intent
Issues: Work items with status tracking (markdown in .sudocode/issues/) - agent work, actionable tasks
Feedback: Anchored comments on specs documenting what happened during implementation
Relationships: Dependency graphs between issues and specs (blocks, implements, parent-child, discovered-from)

Create issues when: Concrete actionable work, can be completed and closed, implements a spec, is a bug/task Create specs when: Documenting user intent and requirements, architecture decisions, API designs, feature specifications

Working with the System

Two Ways to Modify Specs/Issues

Option 1: Direct Markdown Editing (For content-heavy edits)

Edit markdown files in .sudocode/specs/ or .sudocode/issues/
Frontmatter contains metadata (id, title, status, relationships, tags)
Content after frontmatter is the body
System syncs bidirectionally
Use direct markdown editing when possible to maintain file structure and reduce content churn

Option 2: MCP Tools (Recommended for structured operations)

Use upsert_issue, upsert_spec, link, add_feedback tools
Automatically syncs to markdown/sqlite/jsonl
Validates relationships and IDs

When to use each:

MCP tools: Status changes, creating entities, adding relationships, adding feedback
Direct editing: Writing detailed content, refactoring descriptions, bulk editing

Obsidian-Style Mentions

Link specs and issues inline using [[ID]] syntax:

Basic reference:
Implement OAuth per [[s-8h2k]]

With display text:
See [[s-8h2k|authentication spec]] for details

With relationship type:
Must complete [[i-7x9m]]{ blocks } first

Formats supported:
- [[s-14sh]] - basic reference (creates "references" relationship)
- [[i-x7k9]] or [[@i-x7k9]] - with @ prefix
- [[s-3s542|Custom Text]] - with display text
- [[s-x4d6df]]{ blocks } - declares relationship type
- [[s-24gfs3|Text]]{ blocks } - both display and relationship

Read the full file on GitHub · 258 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.

2mo ago First seen · 258 lines · 118 tokens per session scan A 29a02f966049

Subscribe to this mod's changes

sudocode is a skill published in the GitHub repository sudocode-ai/sudocode (296 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 2,104 once invoked, about $0.0005 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 2026-08-30.

Claude Code Planning Project management agents ai automation cli coding-agents

sudocode next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sudocodesudocode-ai/sudocode	Skill	296	7mo ago	Apache-2.0	A	118	Claude Code
agents-market-installertt-a1i/agents-market	Skill	9	2mo ago	MIT	A	43	Claude Code
agents-market-installertt-a1i/agents-market	Skill	9	2mo ago	MIT	A	43	Claude Code, Codex
agents-market-installertt-a1i/agents-market	Skill	9	2mo ago	MIT	A	43	Claude Code, Codex
hyperpod-version-checkerawslabs/agent-plugins	Skill	938	5d ago	Apache-2.0	A	120	Claude Code
directory-managementawslabs/agent-plugins	Skill	938	5d ago	Apache-2.0	A	62	Claude Code
wttr-weatherAtomicBot-ai/atomic-agent	Skill	3.3k	today	MIT	A	25	Claude Code, Codex