Agent skill

Upstream Protocol Drift Watch

by rebornix in rebornix/Agmente

Dynamically inspect ACP and Codex upstream repos using .agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report.

MITAuto-check passedBackend & APIs

Install Upstream Protocol Drift Watch

skills CLI
$ npx skills add rebornix/Agmente --skill upstream-protocol-drift-watch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rebornix/Agmente upstream-protocol-drift-watch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rebornix/Agmente.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/upstream-protocol-drift-watch .claude/skills/upstream-protocol-drift-watch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
upstream-protocol-drift-watch
GitHub stars
545
Token cost
~914 tokens
SKILL.md length
400 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Dynamically inspect ACP and Codex upstream repos using .agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report.

  • Works in 3 steps: Use HEAD..origin/main for each upstream… → If origin/main is unavailable, use… → If HEAD~1 is unavailable, use HEAD..HEAD…
  • Checking for new APIs
  • SKILL.md covers Goal, Inputs, Required Runtime Sources and Dynamic Scan Workflow, plus 3 more sections
  • Calls git and swift

What it does

Upstream Protocol Drift Watch is an agent skill from rebornix/Agmente. Dynamically inspect ACP and Codex upstream repos using .agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report. Use when checking for new APIs, method changes, or protocol/spec changes after upstream updates.

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Backend & APIs, covering OpenAPI specifications. The repository describes itself as: iOS client for coding agents via ACP or Codex app-server. The licence is MIT.

When your agent uses it

  • Checking for new APIs
  • Protocol/spec changes after upstream updates

Example prompts

  • “/upstream-protocol-drift-watch”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Use HEAD..origin/main for each upstream repo.
  2. If origin/main is unavailable, use HEAD~1..HEAD.
  3. If HEAD~1 is unavailable, use HEAD..HEAD and report that no baseline exists.

What it can do on your machine

Read from SKILL.md and the folder at commit 87f224e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • swift

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Upstream Protocol Drift Watch loads about 914 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 400 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~914

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rebornix/Agmente at commit 87f224e, republished under its MIT licence (© rebornix). 400 words, ~914 tokens.

Download SKILL.mdSave it as .claude/skills/upstream-protocol-drift-watch/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
upstream-protocol-drift-watch
description
Dynamically inspect ACP and Codex upstream repos using .agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report. Use when checking for new APIs, method changes, or protocol/spec changes after upstream updates.

Upstream Protocol Drift Watch

Goal

Catch upstream ACP/Codex changes early, especially:

  • new RPC/API methods,
  • removed or renamed methods,
  • protocol/spec file changes that can cause Agmente regressions.

This skill is dynamic by default: always read current local repos and refs at runtime.

Inputs

Collect these from the user request when present:

  • optional from_ref and to_ref (for each repo, or shared),
  • whether to check codex, acp, or both.

If refs are not provided:

  1. Use HEAD..origin/main for each upstream repo.
  2. If origin/main is unavailable, use HEAD~1..HEAD.
  3. If HEAD~1 is unavailable, use HEAD..HEAD and report that no baseline exists.

Always fetch upstream remotes before scanning:

bash
git -C <repo> fetch --all --prune

Required Runtime Sources

  1. Read repo-local path registry:
bash
cat .agmente.paths
  1. Resolve:
  • AGMENTE_CODEX_REPO
  • AGMENTE_ACP_REPO
  1. Validate both paths are git repos before scanning.

Dynamic Scan Workflow

  1. Resolve diff range per repo.
  • Use user-provided refs if given.
  • Otherwise use HEAD..origin/main.
  • Always perform git fetch --all --prune before resolving refs and diff range.
  1. Collect changed files in protocol-relevant areas.
  • Codex focus paths:
    • codex-rs/app-server-protocol
    • codex-rs/app-server
  • ACP focus paths:
    • docs/schema
    • docs/protocol
    • docs/rfds
  1. Extract method-like token changes from patch.
  • Treat quoted/backticked values like foo/bar as method candidates.
  • Track added and removed candidates separately.
  1. Compare against locally supported methods.
  • Codex local method sources:
    • AppServerClient/Sources/AppServerClient/AppServerMethods.swift
    • AppServerClient/Sources/AppServerClient/AppServerEventParser.swift
  • ACP local method sources:
    • ACPClient/Sources/ACPClient/ACP/ACPMethods.swift
    • ACPClient/Sources/ACPClient/ACP/ResponseDispatcher.swift
  1. Build a risk score and severity.
Show full SKILL.md (182 more words)Show less

Risk Scale

  • 0-19: none
  • 20-44: low
  • 45-74: medium
  • 75-100: high

Suggested scoring:

  • Path impact (max 70):
    • protocol/schema core files changed: +35 each bucket
    • app-server runtime/docs changed: +10 to +20
    • RFD/docs-only changes: +8 to +12
  • Method impact (max 30+):
    • added method not recognized locally: +12 each (cap 36)
    • removed method referenced locally: +15 each (cap 45, immediate high priority)
    • payload shape changes on core methods (thread/*, turn/*, session/*): add +10

Escalation rule:

  • Any removed locally referenced method => at least medium.
  • Multiple removed locally referenced methods => high.

Output Contract

Always return:

  1. Summary table: repo, diff range, changed file count, severity, score.
  2. Added unknown methods list.
  3. Removed supported methods list.
  4. Key changed files likely to affect compatibility.
  5. Recommended follow-up tests:
  • swift test --package-path AppServerClient
  • swift test --package-path ACPClient
  • targeted AgmenteTests protocol suites.

Guardrails

  • Do not write or require a persistent baseline file unless user explicitly asks.
  • Do not create new scripts for this check unless user explicitly asks.
  • Prefer live git state and direct diff inspection each run.
  • Do not skip fetch unless user explicitly asks to avoid network operations.

© rebornix, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/upstream-protocol-drift-watch of rebornix/Agmente.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 87f224e

Compare with similar skills

Upstream Protocol Drift Watch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Upstream Protocol Drift Watch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Upstream Protocol Drift Watch this skillrebornix/Agmente545—~914Automated safety check: PassMIT
ToolJet Marketplace Plugin BuilderToolJet/ToolJet41k—~2.1kAutomated safety check: PassAGPL-3.0
Step Partsearthtojake/text-to-cad19k1 repos~1.5kAutomated safety check: PassMIT
OpenAPI to MCP Servermcp-use/mcp-use11k—~5.2kAutomated safety check: PassApache-2.0
Use Yaakmountain-loop/yaak19k—~1.9kAutomated safety check: PassMIT
API DesignerJeffallan/claude-skills12k1 repos~2kAutomated safety check: PassMIT

Similar skills

  • Turns an API description, such as an OpenAPI file or a Postman collection, into a connector plugin for ToolJet's marketplace and checks it with the repo's validator.

    41k GitHub stars~2.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Step Parts

    earthtojake/text-to-cad

    Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers…

    19k GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check passed
  • OpenAPI to MCP Server

    mcp-use/mcp-use

    Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.

    11k GitHub stars~5.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • Use Yaak

    mountain-loop/yaak

    A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…

    19k GitHub stars~1.9k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • API Designer

    Jeffallan/claude-skills

    Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.

    12k GitHub starsUsed in 1 repo~2k tokens
    Backend & APIsAuto-check passed
  • CLI Creator

    huangruiteng/CS-Notes

    Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script.

    4k GitHub starsUsed in 2 repos~2.7k tokens
    Backend & APIsAuto-check passed

More from rebornix/Agmente

  • Codex Local CLI E2E

    rebornix/Agmente

    Run and debug Agmente iOS end-to-end tests against a real local Codex CLI app-server instance.

    545 GitHub stars~625 tokensUpdated 4 mo ago
    Auto-check passed
  • Repeat With Delay

    rebornix/Agmente

    Execute repeated shell commands as separate tool calls with a delay between each iteration.

    545 GitHub stars~473 tokensUpdated 4 mo ago
    Auto-check passed
  • Run Agmente Codex E2E

    rebornix/Agmente

    Run Agmente iOS end-to-end tests against a local Codex app-server endpoint, validate Codex thread/turn protocol flow, and perform mandatory cleanup.

    545 GitHub stars~464 tokensUpdated 4 mo ago
    Auto-check passed
  • Acp Local Runner

    rebornix/Agmente

    Run and debug Agmente ACP end-to-end scenarios from the repo-owned e2e/scenarios/acp specs.

    545 GitHub stars~804 tokensUpdated 4 mo ago
    Auto-check passed
  • Run Agmente E2E

    rebornix/Agmente

    Run Agmente iOS end-to-end tests against a local ACP agent (Gemini, Claude, Qwen, or Vibe), validate core RPC flow, and perform mandatory cleanup.

    545 GitHub stars~414 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Upstream Protocol Drift Watch

What does Upstream Protocol Drift Watch do?

Dynamically inspect ACP and Codex upstream repos using .agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report. Upstream Protocol Drift Watch is an agent skill from rebornix/Agmente.paths, detect protocol/API/spec drift, and produce a risk-scored regression report.

When should I use Upstream Protocol Drift Watch?

Upstream Protocol Drift Watch fits situations like: checking for new APIs; protocol/spec changes after upstream updates.

How do I install Upstream Protocol Drift Watch in Claude Code?

Run `npx skills add rebornix/Agmente --skill upstream-protocol-drift-watch -a claude-code`. Or copy the skill folder (.agents/skills/upstream-protocol-drift-watch in rebornix/Agmente) into .claude/skills/upstream-protocol-drift-watch in your project. Claude Code loads it when a task matches its description.

How do I install Upstream Protocol Drift Watch in Codex?

Run `npx skills add rebornix/Agmente --skill upstream-protocol-drift-watch -a codex`. Or copy the skill folder (.agents/skills/upstream-protocol-drift-watch in rebornix/Agmente) into .agents/skills/upstream-protocol-drift-watch in your project. Codex loads it when a task matches its description.

Can I use Upstream Protocol Drift Watch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rebornix/Agmente --skill upstream-protocol-drift-watch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/upstream-protocol-drift-watch, .gemini/skills/upstream-protocol-drift-watch, .github/skills/upstream-protocol-drift-watch and .opencode/skills/upstream-protocol-drift-watch in your project.

What does Upstream Protocol Drift Watch need to run?

Going by SKILL.md and its folder, Upstream Protocol Drift Watch needs the command-line tools its instructions call (git and swift).

Does Upstream Protocol Drift Watch access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Upstream Protocol Drift Watch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Upstream Protocol Drift Watch use?

Upstream Protocol Drift Watch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Upstream Protocol Drift Watch use?

About 914 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Upstream Protocol Drift Watch?

Skills that share tags, products or a category with Upstream Protocol Drift Watch: ToolJet Marketplace Plugin Builder (ToolJet/ToolJet, 41k stars), Step Parts (earthtojake/text-to-cad, 19k stars), OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars) and Use Yaak (mountain-loop/yaak, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Upstream Protocol Drift Watch?

rebornix (a GitHub user) maintains it in rebornix/Agmente, which has 545 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on May 31, 2026.

Source: rebornix/Agmente on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.