executing
Skill2 starsChanged 8 months agoMITView on GitHub
Execute implementation plan task-by-task inline.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- forsonny/DG-Anviltheir own version, first seen Apr 15, 2026
- LucasDuys/forgetheir own version, first seen Mar 21, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- LucasDuys/forge★ 56same name
- forsonny/DG-Anvil★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- auditingSkill
- bootstrappingSkill
- debuggingSkill
- finalizingSkill
- guardingSkill
- handling-reviewSkill
- ideatingSkill
- isolatingSkill
- orchestratingSkill
- parallelizingSkill
- planningSkill
- precisionSkill
- requesting-reviewSkill
- runbookSkill
- scaffoldingSkill
- skill-craftingSkill
- tddSkill
- verifyingSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
If subagents are available, arsyn:orchestrating produces higher-quality results.
- Distinctive: line 18
Read the plan file.
- Distinctive: line 20
If concerns exist, raise them with the user before starting.
- Distinctive: line 21
If clear, begin execution.
- Distinctive: line 28
Follow each step exactly as written — the plan contains bite-sized steps for a reason.
- Distinctive: line 29
Run every verification command and confirm the expected output.
- Distinctive: line 34
After all tasks pass verification:
- Distinctive: line 47
Ask the user for guidance rather than guessing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Executing
Load a plan, review it critically, run every task in sequence, then hand off to arsyn:finalizing.
Announce at start: "Running plan inline using arsyn:executing."
If subagents are available, arsyn:orchestrating produces higher-quality results. Prefer it when the platform supports subagent dispatch.
Process
1. Load and Review
- Read the plan file.
- Identify questions, gaps, or risks.
- If concerns exist, raise them with the user before starting.
- If clear, begin execution.
2. Task Loop
For each task in the plan:
- Mark task in-progress.
- Follow each step exactly as written — the plan contains bite-sized steps for a reason.
- Run every verification command and confirm the expected output.
- Mark task completed.
3. Completion
After all tasks pass verification:
- Announce: "All tasks complete. Switching to arsyn:finalizing."
- Invoke arsyn:finalizing to run final checks, present options, and close the branch.
When to Stop
Halt execution immediately when:
- A dependency is missing or unavailable.
- A test fails and the cause is not obvious from the plan.
- An instruction is ambiguous or contradictory.
- Verification fails after two attempts.
Ask the user for guidance rather than guessing. Do not force through blockers.
When to Re-Review
Return to step 1 (Load and Review) when:
- The user updates the plan mid-execution.
- A fundamental approach change is needed.
Gotchas
- Skipping verification steps — Every verification in the plan exists to catch drift early. Do not skip them even when the implementation "obviously" works.
- Guessing past blockers — When stuck, stop and ask. Guessing compounds errors across subsequent tasks.
- Executing on main branch — Never start implementation on main/master without explicit user consent. Use arsyn:isolating first.
- Ignoring plan order — Tasks are sequenced for dependency reasons. Do not reorder unless you are certain there is no dependency.
- Forgetting to commit — Each task in the plan ends with a commit step. Skipping commits makes rollback impossible.
- Drifting from the plan — If you spot an improvement, note it but follow the plan as written. Propose changes to the user between tasks.
Integration
- arsyn:isolating — Set up workspace before starting.
- arsyn:planning — Produces the plan this skill consumes.
- arsyn:finalizing — Closes the branch after all tasks complete.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.