Agent skill

Cc Sync Execute Loop

by X-isdoingreat in X-isdoingreat/canvas-pilot

Use only after a reviewed CC-to-Codex sync plan has been approved for execution.

AGPL-3.0Auto-check passedAgent Workflows

Install Cc Sync Execute Loop

skills CLI
$ npx skills add X-isdoingreat/canvas-pilot --skill cc-sync-execute-loop -a claude-code

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

GitHub CLI
$ gh skill install X-isdoingreat/canvas-pilot cc-sync-execute-loop --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/X-isdoingreat/canvas-pilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cc-sync-execute-loop .claude/skills/cc-sync-execute-loop && 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
cc-sync-execute-loop
GitHub stars
125
Token cost
~1.7k tokens
SKILL.md length
841 words
Files
3 (incl. scripts)
Skills in repo
32
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Use only after a reviewed CC-to-Codex sync plan has been approved for execution.

  • Works in 3 steps: runs/codex//REVISED_CC_SYNC_PLAN.md → runs/codex//CC_SYNC_PLAN.md → docs/CODEX_BATCHES.md only when the user…
  • Agent Workflows work in your project
  • SKILL.md covers Boundary, Relationship To cc-sync-runner, Plan Lookup and Loop Modes, plus 7 more sections
  • Runs Python scripts from its folder; calls python

What it does

Cc Sync Execute Loop is an agent skill from X-isdoingreat/canvas-pilot. Use only after a reviewed CC-to-Codex sync plan has been approved for execution. It runs the guarded implementation loop, updates durable plan state, and avoids raw planning or unapproved Canvas work.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/cc_sync_loop_lock.py`).

It sits in Agent Workflows. The repository describes itself as: Local-first Canvas LMS AI agent that learns each course's recurring assignment workflow and reuses it through scan - approval - execute with student review. The licence is AGPL-3.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/cc-sync-execute-loop”

Requirements

  • Python 3

Workflow steps

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

  1. runs/codex//REVISED_CC_SYNC_PLAN.md
  2. runs/codex//CC_SYNC_PLAN.md
  3. docs/CODEX_BATCHES.md only when the user explicitly requested roadmap

What it can do on your machine

Read from SKILL.md and the folder at commit 6b79d5b. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

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

  • Network

    No URLs in SKILL.md.

    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

Cc Sync Execute Loop loads about 1.7k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 841 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from X-isdoingreat/canvas-pilot at commit 6b79d5b, republished under its AGPL-3.0 licence (© X-isdoingreat). 841 words, ~1,732 tokens.

Download SKILL.mdSave it as .claude/skills/cc-sync-execute-loop/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
cc-sync-execute-loop
description
Use only after a reviewed CC-to-Codex sync plan has been approved for execution. It runs the guarded implementation loop, updates durable plan state, and avoids raw planning or unapproved Canvas work.

CC Sync Execute Loop

Run the execution side of the CC-to-Codex workflow. This skill owns the loop, lock, heartbeat, plan-state update, and bounded execution cycle. It does not audit raw Claude Code drift; $cc-sync-runner owns review/planning.

Boundary

  • Consume reviewed and approved plan artifacts; do not create the sync plan from scratch unless the user explicitly redirects to planning.
  • Treat CC_SYNC_PLAN.md / REVISED_CC_SYNC_PLAN.md as durable state. Conversation context is helpful but not authoritative.
  • Preserve scan -> approval -> execute boundaries. Do not execute unapproved work.
  • Keep .claude/ and CLAUDE.md read-only.
  • Do not copy private course playbooks, real course IDs, private URLs, instructor names, emails, or identity details into Codex artifacts.
  • Do not submit to Canvas, answer quizzes, upload files, push upstream, or run live external actions from this skill.

Relationship To cc-sync-runner

Use $cc-sync-runner for:

  • generating runs/codex/<today>/CC_SYNC_PLAN.md
  • reviewing raw sync plans
  • writing REVISED_CC_SYNC_PLAN.md, CAPABILITY_GAPS.md, PROPOSED_BATCHES.md, and NEW_SKILL_SPECS.md
  • deciding public/private sync classification

Use $cc-sync-execute-loop only after the user approves the reviewed plan or approved batch.

If approval or reviewed plan evidence is missing, write a blocker in the loop state and stop. Do not silently fall back into planning.

Plan Lookup

Prefer artifacts in this order:

  1. runs/codex/<today>/REVISED_CC_SYNC_PLAN.md
  2. runs/codex/<today>/CC_SYNC_PLAN.md
  3. docs/CODEX_BATCHES.md only when the user explicitly requested roadmap continuation rather than CC drift execution

Always read AGENTS.md before executing a cycle.

Loop Modes

One-Shot Tick

Default mode. Run exactly one guarded cycle, update the plan state, release the lock, and report.

Use this mode when an external scheduler invokes Codex every 10 minutes.

Same-Dialog Persistent Loop

Use only when the user explicitly asks for a loop, wake every 10 minutes, keep going, auto-continue, or run until blocked.

After each successful cycle:

  1. Release the lock.
  2. Report the next scheduled wake time.
  3. Run Start-Sleep -Seconds 600.
  4. Start the next cycle in the same conversation.

The 10-minute delay starts after the previous cycle finishes. If a cycle takes longer than 10 minutes, do not overlap it with another cycle.

Lock Helper

Use the bundled script for lock and heartbeat state:

powershell
python .agents\skills\cc-sync-execute-loop\scripts\cc_sync_loop_lock.py claim --root . --ttl-minutes 30
python .agents\skills\cc-sync-execute-loop\scripts\cc_sync_loop_lock.py heartbeat --root .
python .agents\skills\cc-sync-execute-loop\scripts\cc_sync_loop_lock.py release --root .
python .agents\skills\cc-sync-execute-loop\scripts\cc_sync_loop_lock.py status --root .

The lock file is .codex/cc-sync-execute-loop.lock.json.

If claim reports a fresh active lock:

  • in one-shot mode, stop and report that another cycle is active
  • in same-dialog loop mode, sleep 10 minutes and retry

If the lock is stale, the script claims a new cycle and records the recovered lock in recovered_from.

Heartbeat before and after long checks, tests, or edits.

Loop State Block

Keep or create this block near the top of the active plan artifact:

markdown
<!-- CC_SYNC_EXECUTE_LOOP_STATE v1 -->
## Execute Loop State

- status: idle | active | blocked | sleeping | complete
- mode: one-shot | same-dialog-loop
- active_batch: none | B<N>
- active_step: short text
- last_completed_step: short text
- next_step: short text
- approval_source: user-message | plan | none
- lock_owner: cycle id or none
- updated_at: ISO-8601 timestamp
- blocker: none or concrete blocker
<!-- /CC_SYNC_EXECUTE_LOOP_STATE -->

Update this block after every material action. If the active plan lacks the block, add it before making execution edits.

Cycle

For each cycle:

  1. Read AGENTS.md.
  2. Read the active plan artifact using the lookup order above.
  3. Confirm explicit execution approval.
  4. Claim the lock.
  5. Update loop state to active.
  6. Determine the next bounded execution unit.
  7. Execute that unit.
  8. Run the relevant verification.
  9. Update loop state with completed work, next step, and blockers.
  10. Release the lock.
  11. In same-dialog loop mode, sleep 10 minutes unless blocked or complete.
Show full SKILL.md (333 more words)Show less

Next Unit Selection

Choose the next unit in this order:

  1. Continue the single batch already marked in_progress in docs/CODEX_BATCHES.md.
  2. If no batch is in progress, claim the earliest approved batch named by the reviewed plan.
  3. If roadmap continuation was explicitly requested, choose the earliest eligible status: next batch.
  4. If no approved unit exists, mark the loop blocked with approval_source: none and stop.

Claim only one batch. Do not skip batch order.

Execution Unit

Within one cycle, prefer one concrete repair loop:

  1. Run python scripts\codex_check.py --batch B<N>.
  2. If it passes, write the batch report and mark the batch done.
  3. If it fails, read the first actionable assertion.
  4. Confirm the needed edit is inside the batch's allowed files.
  5. Make the smallest Codex-side edit.
  6. Rerun the same batch check.
  7. Update loop state.

If the user explicitly requested "run until blocked", the cycle may continue within the same active batch until the batch passes or a hard stop occurs. Do not continue into a second batch without an explicit roadmap/loop instruction.

Reports

When a batch passes, write:

text
runs/codex/<today>/PARITY_B<N>.md

Include:

  • scope
  • changed files
  • check results
  • warnings
  • whether .claude/ was touched
  • next batch recommendation

Then update public-safe Codex tracking docs named by the approved plan, such as docs/CODEX_BATCHES.md and docs/CODEX_PARITY_MATRIX.md.

Do not update the CC baseline unless the reviewed plan explicitly approved it and all impacted checks pass.

Hard Stops

Stop, update loop state to blocked, release the lock, and report if:

  • execution approval is missing or ambiguous
  • the active plan has not been reviewed
  • the next edit would touch .claude/ or CLAUDE.md
  • the next edit needs private course details or live user identity
  • the next action would submit, upload, answer a quiz, push upstream, or call a live Canvas endpoint
  • the needed edit is outside the active batch's allowed files
  • codex_check.py fails for an environment problem unrelated to the batch
  • the same assertion fails twice after a repair without new evidence
  • the user interrupts or redirects the loop

© X-isdoingreat, AGPL-3.0. 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 2 other files (scripts) in .agents/skills/cc-sync-execute-loop of X-isdoingreat/canvas-pilot.

  • SKILL.md
  • agents/openai.yaml
  • scripts/cc_sync_loop_lock.py

Open the folder on GitHubat commit 6b79d5b

Compare with similar skills

Cc Sync Execute Loop 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.

Cc Sync Execute Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cc Sync Execute Loop this skillX-isdoingreat/canvas-pilot125—~1.7kAutomated safety check: PassAGPL-3.0
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

More from X-isdoingreat/canvas-pilot

All 32 skills in this repo
  • Daily Work Tweet

    X-isdoingreat/canvas-pilot

    A skill your agent uses when verified work from today or another day should become an X/Twitter post, build-in-public update, ship log, or bilingual draft.

    125 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Canvas Awkward Syntax

    X-isdoingreat/canvas-pilot

    A skill your agent uses when a short local academic draft needs role-aware syntax diversification while preserving meaning, locks, source grounding, rubric-critical openings, and document structure.

    125 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Canvas Cron

    X-isdoingreat/canvas-pilot

    A skill your agent uses when managing Canvas Pilot schedules: install, inspect, pause, change, delete, or safely test scheduled scans and runs.

    125 GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check: notes
  • Canvas Essay

    X-isdoingreat/canvas-pilot

    A skill your agent uses for an approved long academic-writing assignment routed by canvas-execute after the deterministic writing router selects essay.

    125 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Canvas Generic

    X-isdoingreat/canvas-pilot

    A skill your agent uses for an approved Canvas assignment that no specialized course skill can handle.

    125 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Canvas Humanizer

    X-isdoingreat/canvas-pilot

    A skill your agent uses when a local academic draft needs a meaning-preserving humanizing pass with less uniform syntax while retaining rubric, source, lock, voice, and length constraints.

    125 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Cc Sync Execute Loop

What does Cc Sync Execute Loop do?

Use only after a reviewed CC-to-Codex sync plan has been approved for execution. Cc Sync Execute Loop is an agent skill from X-isdoingreat/canvas-pilot. Use only after a reviewed CC-to-Codex sync plan has been approved for execution.

When should I use Cc Sync Execute Loop?

Cc Sync Execute Loop fits situations like: agent Workflows work in your project.

How do I install Cc Sync Execute Loop in Claude Code?

Run `npx skills add X-isdoingreat/canvas-pilot --skill cc-sync-execute-loop -a claude-code`. Or copy the skill folder (.agents/skills/cc-sync-execute-loop in X-isdoingreat/canvas-pilot) into .claude/skills/cc-sync-execute-loop in your project. Claude Code loads it when a task matches its description.

How do I install Cc Sync Execute Loop in Codex?

Run `npx skills add X-isdoingreat/canvas-pilot --skill cc-sync-execute-loop -a codex`. Or copy the skill folder (.agents/skills/cc-sync-execute-loop in X-isdoingreat/canvas-pilot) into .agents/skills/cc-sync-execute-loop in your project. Codex loads it when a task matches its description.

Can I use Cc Sync Execute Loop 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 X-isdoingreat/canvas-pilot --skill cc-sync-execute-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cc-sync-execute-loop, .gemini/skills/cc-sync-execute-loop, .github/skills/cc-sync-execute-loop and .opencode/skills/cc-sync-execute-loop in your project.

What does Cc Sync Execute Loop need to run?

Going by SKILL.md and its folder, Cc Sync Execute Loop needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Cc Sync Execute Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cc Sync Execute Loop 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cc Sync Execute Loop use?

Cc Sync Execute Loop is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cc Sync Execute Loop use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Cc Sync Execute Loop?

Skills that share tags, products or a category with Cc Sync Execute Loop: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cc Sync Execute Loop?

X-isdoingreat (a GitHub user) maintains it in X-isdoingreat/canvas-pilot, which has 125 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on July 31, 2026.

Source: X-isdoingreat/canvas-pilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.