fnl-delegate
Skill4 starsChanged 14 days agoMITView on GitHub
Hand work to other coding agents (Claude Code, Codex, Antigravity) and run it, coordinating from whichever one you run in. Use whenever work is split across agents or needs a routing decision: giving a task to another agent, choosing the agent and model for each of several tasks, running independent tasks in parallel, an agent's quota running out, a delegated run you are watching that stalls, times out or is interrupted, or running a spec as a coordinator with one session per task. Writing the brief for a single task, or saving a handover, belongs to fnl-handoff.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- finolabs/vibecodetheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- finolabs/vibecode★ 4same 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 repository19 other files it gives its agents.
- rules/AGENTS.mdAGENTS.md
- skills/fnl-delegate/references/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- fnl-advisorSkill
- fnl-askSkill
- fnl-coding-routerSkill
- fnl-commit-messagesSkill
- fnl-handoffSkill
- fnl-open-source-reviewSkill
- fnl-plugin-packagingSkill
- fnl-restore-pointSkill
- fnl-review-gateSkill
- fnl-security-review-gateSkill
- fnl-session-hygieneSkill
- fnl-setupSkill
- fnl-statusSkill
- fnl-updateSkill
- fnl-verificationSkill
- fnl-versioningSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 11 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read references/entry.md before dispatch: canonical host config, dependencies and references.
- Distinctive: line 12
Read references/delegation-mode.md for this step.
- Very specific: line 18
Read references/loop.md: grade, route, brief, dispatch, watch, accept, record.
- Distinctive: line 23
Read references/grade.md for this step.
- Distinctive: line 26
Read references/route.md for this step.
- Distinctive: line 32
Follow the accounting rule in references/route.md.
- Distinctive: line 36
Read references/capabilities-and-budget.md for this step.
- Distinctive: line 40
Read references/parallel-dispatch.md for family pools and advisory slots.
- Distinctive: line 44
Read references/budget-and-liveness.md for this step.
- Distinctive: line 48
Read references/heavy-jobs.md for this step.
- Very specific: line 52
Use fnl-verification "Accepting someone else's work".
- Distinctive: line 56
Read references/handover-after-an-interrupted-run.md for this step.
- Distinctive: line 60
Read references/where-files-go.md for this step.
≈ “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
Delegate
Read references/entry.md before dispatch: canonical host config, dependencies and references; project rules win.
Delegation mode
Read references/delegation-mode.md for this step.
Offer neutral Yes and No choices with none preselected or marked recommended; a default, a timeout or an auto-selected option never counts as the yes.
The loop
Read references/loop.md: grade, route, brief, dispatch, watch, accept, record; name runs as fnl-session-hygiene "Titles" says.
Accept starts with log_scan.py scan <log> and log_scan.py show <log>; finish uses ledger.py finish --log-path <log>.
Report a leak by name, never chase it; the reference owns redaction and the environment-only residual-risk report.
Grade
Read references/grade.md for this step.
Route
Read references/route.md for this step.
For reviews, route reviews with review_route.py; the reference retains reachability and quota checks.
Keep or hand off
Follow the accounting rule in references/route.md.
Capabilities and budget
Read references/capabilities-and-budget.md for this step.
Parallel dispatch
Read references/parallel-dispatch.md for family pools and advisory slots.
Budget and liveness
Read references/budget-and-liveness.md for this step.
Heavy jobs
Read references/heavy-jobs.md for this step.
Accept
Use fnl-verification "Accepting someone else's work"; read references/accept.md for the receipt gate and explicit exception. The coordinator retains the verdict.
Handover after an interrupted run
Read references/handover-after-an-interrupted-run.md for this step.
Where files go
Read references/where-files-go.md for this step.
Ledger
Record every dispatch with scripts/ledger.py in this skill's base directory, at the moment it happens: a start line at dispatch, a finish line when the run is accepted, rejected or stopped. Commands, the agent values and what summary reports are in references/ledger.md. The ledger holds short task labels only: no task data, secrets or personal data.
Related skills
fnl-handoff: write the brief and dispatch one task.fnl-advisor: one second opinion or two contrasting families for root cause or planning when stuck, all read-only.fnl-status: the usage dashboard (router coverage, skill use, load cost, delegation, review gate) and the runs still open.
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.