New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Code Execute Staged Plan

by open-thoughts in open-thoughts/OpenThoughts-Agent

EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Code Execute Staged Plan

skills CLI
$ npx skills add open-thoughts/OpenThoughts-Agent --skill code-execute-staged-plan -a claude-code

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

GitHub CLI
$ gh skill install open-thoughts/OpenThoughts-Agent code-execute-staged-plan --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/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-execute-staged-plan .claude/skills/code-execute-staged-plan && 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
code-execute-staged-plan
GitHub stars
301
Token cost
~977 tokens
SKILL.md length
423 words
Files
1
Skills in repo
44
Repo updated
First seen
Licence
Apache-2.0

At a glance

EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated…

  • Works in 6 steps: Re-read the stage scope + RECONFIRM… → Edit the local feature branch. The… → Run the validation gate, in order → …
  • The user says execute/run the plan
  • SKILL.md covers Inputs, Per-stage loop, Progress-log discipline… and Subagents (for parallel stages…, plus 1 more section
  • Calls git

What it does

Code Execute Staged Plan is an agent skill from open-thoughts/OpenThoughts-Agent. EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated agentlogs/ progress log. For each stage: re-read the scope + reconfirm the (drifting) code anchors, make the edit in the LOCAL clone on the feature branch, run the validation gate (flag-off byte-identical FIRST, then behavior-on / parity / GPU smoke on the right SIF/env), commit+push and sync to the cluster (vLLM = build from…

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with vLLM. The repository describes itself as: Data recipes and robust infrastructure for training AI agents. The licence is Apache-2.0.

When your agent uses it

  • The user says execute/run the plan
  • Continue the <X port/fix

Example prompts

  • “t lose context. Use when the user says”
  • “do stage N”
  • “continue the <X port/fix”
  • “/code-execute-staged-plan”

Requirements

  • Python 3

Workflow steps

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

  1. Re-read the stage scope + RECONFIRM anchors. The borrow-map line/file anchors drift — grep/open the real files now; don't trust line…
  2. Edit the local feature branch. The clones are under ~/Documents/; never hand-edit or patch-by-rsync a cluster. Keep the diff minimal.
  3. Run the validation gate, in order
  4. Commit, push, and sync. One descriptive commit per stage/logical unit. git pull the editable Python repos on the cluster; build vLLM from…
  5. Record results: update the stage scope and parent status (Stage N ✅ DONE — commit , gate ); append what changed, commit, gate numbers…
  6. Advance only on GREEN. A red/ambiguous gate stops the loop — diagnose (dispatch an investigative subagent if it's deep), log it, fix…

What it can do on your machine

Read from SKILL.md and the folder at commit 3bd1917. 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

    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

Code Execute Staged Plan loads about 977 tokens when it runs. Until then it costs about 201 tokens; SKILL.md has 423 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~201
When it runs · the whole SKILL.md, loaded when a task matches
~977

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 open-thoughts/OpenThoughts-Agent at commit 3bd1917, republished under its Apache-2.0 licence (© open-thoughts). 423 words, ~977 tokens.

Download SKILL.mdSave it as .claude/skills/code-execute-staged-plan/SKILL.md (or your agent's skills folder).
name
code-execute-staged-plan
description
EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase>/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated agent_logs/ progress log. For each stage: re-read the scope + reconfirm the (drifting) code anchors, make the edit in the LOCAL clone on the feature branch, run the validation gate (flag-off byte-identical FIRST, then behavior-on / parity / GPU smoke on the right SIF/env), commit+push and sync to the cluster (vLLM = build from source, never rsync), update the plan status, and only THEN advance. Log every stage/debug session in agent_logs/YYYY-MM-DD_<topic>.md so long runs don't lose context. Use when the user says "execute/run the plan", "do stage N", or "continue the <X> port/fix".

code-execute-staged-plan

Run a staged plan one stage, gate, and commit at a time. Keep the plan in notes/<codebase>/ and a dated progress log in agent_logs/.

Inputs

  • The plan: notes/<codebase>/{README.md | <change>_plan.md} + the per-stage stage<N>_<slug>_scope.md. Read the parent (goal + invariants + stage map) and the current stage's scope doc.
  • The progress log: a dated agent_logs/YYYY-MM-DD_<topic>.md — the running record for this change. If one exists for the change, append; else create it.

Per-stage loop

  1. Re-read the stage scope + RECONFIRM anchors. The borrow-map line/file anchors drift — grep/open the real files now; don't trust line numbers from the plan's authoring date.
  2. Edit the local feature branch. The clones are under ~/Documents/; never hand-edit or patch-by-rsync a cluster. Keep the diff minimal.
  3. Run the validation gate, in order:
    • Flag-off byte-identical first — prove the change is a no-op when its flag is off (torch.equal / golden test / the EP-CP no-op test pattern).
    • Behavior-on / parity — the stage's GO condition (e.g. dcp=N==dcp=1 greedy bit-identical + logprobs allclose at the bf16 floor tol — don't loosen tol to pass).
    • GPU smoke where needed via sbatch on the correct SIF/env (.agents/ops/<cluster>/ENVIRONMENT_MAP.md; torch selects the runtime).
    • Lint/syntax via mcp__ide__getDiagnostics, not py_compile.
  4. Commit, push, and sync. One descriptive commit per stage/logical unit. git pull the editable Python repos on the cluster; build vLLM from the committed source. Verify the cluster clone is at the pushed commit and clean.
  5. Record results: update the stage scope and parent status (Stage N ✅ DONE — commit <sha>, gate <result>); append what changed, commit, gate numbers, blocker, and next step to agent_logs/.
  6. Advance only on GREEN. A red/ambiguous gate stops the loop — diagnose (dispatch an investigative subagent if it's deep), log it, fix, re-gate. Don't paper over a failing parity gate.
Show full SKILL.md (139 more words)Show less

Progress-log discipline (agent_logs/)

  • One dated file per change/debug thread (YYYY-MM-DD_<topic>.md); append across stages and sessions.
  • Capture: the hypothesis, what was tried, commit SHAs, gate results (with numbers), what was ruled out, and the current blocker + next action. Future-you (or a fresh subagent) should be able to resume from the log alone.
  • This log is ALSO the per-change failure/remediation record the cron sweep references for genuine FAILED jobs.

Subagents (for parallel stages / deep investigations)

Dispatch with: edit local → commit/push → sync; secrets via env vars only (source "$DC_AGENT_SECRET_ENV"); reconfirm anchors; run and report the gate. Verify the gate claim before marking a stage DONE.

On completion

When the final stage is green, mark the parent plan DONE with the commit range and headline gate, ensure the canonical branch and clusters are current, and write the closing agent_logs/ entry. Note concrete follow-ups.

© open-thoughts, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/code-execute-staged-plan of open-thoughts/OpenThoughts-Agent.

Open the folder on GitHubat commit 3bd1917

Compare with similar skills

Code Execute Staged Plan 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.

Code Execute Staged Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Execute Staged Plan this skillopen-thoughts/OpenThoughts-Agent301—~977Automated safety check: PassApache-2.0
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
CI Fails Buildkiteguqiong96/Lvllm4642 repos~349Automated safety check: PassApache-2.0
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence
Vllm Metax Model UpgradeMetaX-MACA/vLLM-metax179—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

  • CI Fails Buildkite

    guqiong96/Lvllm

    Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

    464 GitHub starsUsed in 2 repos~349 tokens
    AI & LLM EngineeringAuto-check passed

  • Gptqmodel Tokenizer Normalization

    ModelCloud/GPTQModel

    Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Vllm Metax Model Upgrade

    MetaX-MACA/vLLM-metax

    Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels.

    179 GitHub stars~2.6k tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed

  • Vllm Rlt Review PR

    ThinkFlowLab/vllm-rlt

    Review PRs and local changes for hsliuustc0106/vllm-rlt: Ouro engine and KV correctness, serving behavior, and BF16 accuracy/speed evidence.

    138 GitHub stars~1.1k tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

More from open-thoughts/OpenThoughts-Agent

All 44 skills in this repo

  • Analyze Dataset Token Length

    open-thoughts/OpenThoughts-Agent

    Analyze the token length of an OT-Agent conversation-format (ShareGPT-style) dataset — the per-trace distribution (median/p90/max) and/or counts under a token threshold + a metadata predicate (e.g.

    301 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Id Eval Ranking

    open-thoughts/OpenThoughts-Agent

    Given a list of models (HF name stubs) that have valid agentic ID eval scores in Supabase, build a ranking table: raw per-benchmark accuracy on the 3 ID benchmarks (SWE-Bench-100…

    301 GitHub stars~3.1k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Job History Iris

    open-thoughts/OpenThoughts-Agent

    Run the Iris harbor job-history analyzer (scripts/iris/analyzeirisharborjob.py) on a datagen/eval job and read its JSON sidecar for trustworthy throughput / preemption / productive-trial stats.

    301 GitHub stars~2.9k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Rl Behavior

    open-thoughts/OpenThoughts-Agent

    Run the full RL behavioral-analysis pipeline (scripts/analysis/analyzerlbehavior.py) on a trained RL model to understand WHAT changed vs its pre-RL baseline, WHY, whether it PERSISTS, and its EVAL…

    301 GitHub stars~4.2k tokensUpdated 9 days ago
    Auto-check passed

  • Analyze Training Run Iris

    open-thoughts/OpenThoughts-Agent

    Detailed health check for a Levanter/executor TRAINING run on the marin Iris cluster (e.g.

    301 GitHub stars~2k tokensUpdated 9 days ago
    Auto-check passed

  • Code Create Staged Plan

    open-thoughts/OpenThoughts-Agent

    DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…

    301 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check passed

Works with

Categories

Questions about Code Execute Staged Plan

What does Code Execute Staged Plan do?

EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated…. Code Execute Staged Plan is an agent skill from open-thoughts/OpenThoughts-Agent. EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated agentlogs/ progress log.

When should I use Code Execute Staged Plan?

Code Execute Staged Plan fits situations like: the user says execute/run the plan; continue the <X port/fix.

How do I install Code Execute Staged Plan in Claude Code?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill code-execute-staged-plan -a claude-code`. Or copy the skill folder (.agents/skills/code-execute-staged-plan in open-thoughts/OpenThoughts-Agent) into .claude/skills/code-execute-staged-plan in your project. Claude Code loads it when a task matches its description.

How do I install Code Execute Staged Plan in Codex?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill code-execute-staged-plan -a codex`. Or copy the skill folder (.agents/skills/code-execute-staged-plan in open-thoughts/OpenThoughts-Agent) into .agents/skills/code-execute-staged-plan in your project. Codex loads it when a task matches its description.

Can I use Code Execute Staged Plan 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 open-thoughts/OpenThoughts-Agent --skill code-execute-staged-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-execute-staged-plan, .gemini/skills/code-execute-staged-plan, .github/skills/code-execute-staged-plan and .opencode/skills/code-execute-staged-plan in your project.

What does Code Execute Staged Plan need to run?

Going by SKILL.md and its folder, Code Execute Staged Plan needs the command-line tools its instructions call (git). Our summary lists: Python 3.

Does Code Execute Staged Plan 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 Code Execute Staged Plan 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 Code Execute Staged Plan use?

Code Execute Staged Plan is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Execute Staged Plan use?

About 977 tokens (SKILL.md is roughly 3.9k 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 Code Execute Staged Plan?

Skills that share tags, products or a category with Code Execute Staged Plan: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), CI Fails Buildkite (guqiong96/Lvllm, 464 stars) and Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Execute Staged Plan?

open-thoughts (a GitHub organization) maintains it in open-thoughts/OpenThoughts-Agent, which has 301 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on September 28, 2026.

Source: open-thoughts/OpenThoughts-Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.