agent-protocol
Human and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.
Best use case
agent-protocol is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Human and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.
Teams using agent-protocol should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-protocol-majiayu000/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-protocol Compares
| Feature / Agent | agent-protocol | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Human and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Agent Protocol Coordinate work in repos that use `.agentprotocol/`. Keep work items self-contained and minimize follow-up questions. ## Always load first - Read `.agentprotocol/README.md` at the start of any session. - If `.agentprotocol/` is missing, offer to initialize with `bun ./skills/agent-protocol/scripts/init.ts`. ## Core structure - `.agentprotocol/README.md`: protocol contract and Active Work Index. - `.agentprotocol/TODO.md`: intake queue. - `.agentprotocol/open/<ID>-<slug>/`: active work items. - `.agentprotocol/archive/<ID>-<slug>/`: completed or cancelled items (moved as a whole). ## Workflow 1. Intake work in `.agentprotocol/TODO.md`. 2. Create a work item with `create.ts` (build-only by default; add `--plan` for plan + build). 3. Write or refine `plan.md` if needed; keep it flexible (PRDs, user stories, specs). 4. Execute from `build.md` with tasks, verification, and append-only log. 5. Archive by moving the whole directory to `.agentprotocol/archive/`. ## Work selection - If the user names a path or ID, use it. - If not, suggest up to 3 candidates from the Active Work Index and TODO. The user chooses. - Never auto-select. ## plan.md - Optional design surface. May include PRDs, user stories, acceptance criteria, constraints, and invariants. - Frontmatter: `id`, `title`, `status`, `created_at`, `updated_at`, optional `refs`. - `status` values: `draft | ready | done | cancelled`. - `ready` means Open Questions is empty (or risks explicitly accepted). ## build.md - Execution surface with tasks, verification, and append-only log. - May exist without a plan (ad-hoc). - Frontmatter: `id`, `status`, `created_at`, `updated_at`, optional `plan_id`. - `status` values: `todo | in_progress | blocked | done | cancelled`. - If `build/` exists, include a Build File Index table listing all `build/*.md` (sorted by path). - `build/*.md` files are plain markdown by default (no required frontmatter). ## Active Work Index - `.agentprotocol/README.md` contains a markdown table of all open work item directories. - Update with `bun ./skills/agent-protocol/scripts/reindex.ts` (deterministic; avoids manual edits). - Use `--next` to include next-action extraction when desired. ## IDs and timestamps - `ID` is Crockford base32 encoding of UUIDv7 bytes. - Uppercase, fixed 26 chars, left-padded with `0`. - Alphabet: `0123456789ABCDEFGHJKMNPQRSTVWXYZ`. - No zero padding in body identifiers (use `US-1`, not `US-001`). - `created_at` / `updated_at` use RFC3339 with timezone (recommend UTC `Z`). ## Archiving - When a work item is `done | cancelled`, move the entire directory from `open/` to `archive/`. - Remove the row from the Active Work Index. ## Migration - For old `context/` repos, follow `references/migration.md`.
Related Skills
data-structure-protocol
Give agents persistent structural memory of a codebase — navigate dependencies, track public APIs, and understand why connections exist without re-reading the whole repo.
async-repl-protocol
Async REPL Protocol
architectural-amendment-protocol
Amend architectural specifications through formal protocol.
analyzing-protocols
Analyzes network protocol implementations to identify parsing vulnerabilities, state machine issues, and protocol-level security problems. Use when analyzing network servers, protocol handlers, or investigating protocol implementation bugs.
alto-protocol
Use when working with ALTO protocol files - runs/state.json, runs/handoffs/*.md, runs/tasks/*.md, runs/plan.md, or runs/milestones.md. Reference for file formats and state machine.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
mcp-create-declarative-agent
Skill converted from mcp-create-declarative-agent.prompt.md
MCP Architecture Expert
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
mathem-shopping
Automatiserar att logga in på Mathem.se, söka och lägga till varor från en lista eller recept, hantera ersättningar enligt policy och reservera leveranstid, men lämnar varukorgen redo för manuell checkout.
math-modeling
本技能应在用户要求"数学建模"、"建模比赛"、"数模论文"、"数学建模竞赛"、"建模分析"、"建模求解"或提及数学建模相关任务时使用。适用于全国大学生数学建模竞赛(CUMCM)、美国大学生数学建模竞赛(MCM/ICM)等各类数学建模比赛。
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.