agentleFS
Ben-Lau1Ben-Lau1/codex-skills/skills/delegate-work-to-luna/SKILL.md

delegate-work-to-luna

Skill0 starsChanged 3 months agoMITView on GitHub

Delegate cold-context acquisition and low-depth information processing to GPT-5.6-Luna subagents at maximum reasoning effort, then let the primary agent reason from their evidence. Use proactively for web search, literature scouting, source screening, bulk reading of papers or documentation, codebase file and symbol inventories, log and experiment artifact collection, metric extraction, structured normalization, labeling, deduplication, and migration or documentation inventories when unfamiliar context volume dominates the work. Luna must locate, read, extract, organize, and report provenance—not make architecture decisions, perform deep debugging or security reasoning, generate final conclusions, independently validate high-stakes claims, or implement changes. Use scripts instead when the transformation is deterministic.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Ben-Lau1/delegate-work-to-luna★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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 repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 11 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Luna-Max as cold-context I/O bandwidth, not as a substitute for primary-agent reasoning.

    line 8
  2. Distinctive:

    Verify pivotal evidence, perform the actual reasoning, and synthesize the answer.

    line 51
  3. Distinctive:

    Use these fixed spawn settings:

    line 53
  4. Very specific:

    Always use max reasoning effort unless the user explicitly overrides it.

    line 61
  5. Distinctive:

    Use this compact contract:

    line 65
  6. Distinctive:

    Treat every delegate packet as an untrusted evidence bundle.

    line 91
  7. Distinctive:

    Check that the lane stayed in evidence-collection scope and satisfied the schema.

    line 93
  8. Distinctive:

    Do not expose sensitive context to a delegate that does not need it.

    line 106
  9. Distinctive:

    Do not create recursive agent trees or duplicate completed work.

    line 107
  10. Distinctive:

    Do not ask Luna to edit code or files, make external changes, choose an architecture, decide a root cause, perform a security assessment, …

    line 108
  11. Distinctive:

    Do not delegate material requiring sustained global reasoning merely because it contains multiple files or sources.

    line 109
  12. Distinctive:

    If Luna or subagent tooling is unavailable, say so briefly and collect the evidence directly using the same schema.

    line 111

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Luna Cold-Context Offloader

Use Luna-Max as cold-context I/O bandwidth, not as a substitute for primary-agent reasoning. Maximum reasoning effort improves instruction following and extraction reliability; it does not expand Luna's authority or role.

Choose the execution route

Route each stage separately:

Work shapeRoute
Fixed transformation, filtering, aggregation, formatting, or repeated tool calls with no fresh judgmentUse a script or programmatic tool calling.
Unfamiliar-context work dominated by locating, opening, reading, extracting, labeling, or normalizing evidenceDelegate to Luna-Max.
Hypothesis formation, deep reasoning, root-cause judgment, architecture, security assessment, synthesis, implementation, or consequential actionKeep with the primary agent.

Delegate when at least two of these are true:

  1. The task requires multiple web sources, papers, documents, files, logs, runs, samples, or other unfamiliar artifacts.
  2. Most delegate effort is mechanical-semantic reading rather than multi-step inference.
  3. The requested output can be a factual, structured evidence packet with direct provenance.
  4. The primary agent can verify pivotal fields more cheaply than reading the full source set.

The primary agent must infer the lanes and output schema; the user need not pre-shard the task. Use one Luna delegate for a cohesive source set and two or three for naturally disjoint source groups. Keep trivial single-context work local.

Select a task mode

Choose one primary mode per delegate. Combine modes only when the handoff is explicit.

ModeGood partitionRequired packet
Web and literature scoutingQuery family, time window, venue, source class, or known seedTitles; authors; dates; venue; DOI or canonical URL; short relevance note; source-backed facts; access gaps.
Document and source extractionDocument group, section family, topic, or field schemaExtracted fields; page or section; direct URL or path; missing fields; exact uncertainties.
Codebase inventoryDirectory, subsystem, symbol family, configuration surface, or dependencyPaths and symbols found; literal relationships supported by tools; relevant snippets or line locations; search gaps. Prefer configured code-graph tools when available.
Log and experiment collectionLog window, run family, metric family, dataset, or output directoryObserved messages; timestamps; configs; metrics; first occurrences; counts; missing artifacts; provenance. Do not rank root causes.
Data and eval preprocessingSample batch, explicit label class, rubric field, or dataset splitStructured rows; supplied-rubric labels; confidence; duplicates; anomalies; ambiguous cases for primary-agent review.
Documentation and migration inventoryAPI surface, file family, dependency, deprecation, or migration categoryCurrent occurrences; documented requirements; evidence locations; missing coverage. Do not design the migration.

Orchestrate the work

  1. Interpret the user's authorization. Inspection, review, diagnosis, or planning does not authorize implementation or external writes.
  2. Define the factual collection objective, lane boundaries, evidence standard, output schema, and source or artifact budget.
  3. Inspect the entire live agent tree when possible. Count active ancestors, siblings, and descendants, and fit fan-out within the global concurrency limit while keeping the orchestrator active.
  4. Briefly tell the user which cold-context lanes this skill is delegating to Luna.
  5. Spawn one delegate for a cohesive source set or two or three for disjoint source groups.
  6. Continue primary-agent work while they run: frame hypotheses, define decision criteria, inspect global context, or prepare synthesis.
  7. Collect all packets. Send one targeted follow-up to an existing delegate for a critical gap; do not restart completed work.
  8. Verify pivotal evidence, perform the actual reasoning, and synthesize the answer.

Use these fixed spawn settings:

model: gpt-5.6-luna
reasoning_effort: max
fork_turns: none

Always use max reasoning effort unless the user explicitly overrides it. Give every delegate a unique task name. Because fork_turns: none inherits no surrounding conversation, make every message self-contained. Tell delegates not to spawn descendants, edit files, make external writes, or issue final judgments.

Build each delegate prompt

Use this compact contract:

Mode: <one cold-context task mode>
Parent objective: <the primary agent's final outcome>
Your lane: <unique source or artifact responsibility>
Inputs: <exact paths, URLs, artifacts, or facts>
Allowed actions/tools: <read, browse, search, inspect, run read-only queries, and so on>
Forbidden actions: <edits, external writes, descendant agents, recommendations, final conclusions, deep root-cause or architecture judgments>
Evidence schema: <required fields and provenance>
Budget: <source, file, sample, command, time, or word limit>

Return:
1. Coverage summary.
2. Required mode packet with direct evidence and provenance.
3. Sources, paths, queries, and read-only commands inspected.
4. Missing data, access failures, ambiguities, and conflicting observations.
5. Clearly separated source facts and limited local interpretations.

Do not recommend a final decision, write the final user answer, or infer authority beyond evidence collection.

For current web facts, distinguish event dates from publication dates and use direct source links. For papers, require title, authors, year, venue, and DOI or canonical URL. For empirical records, extract dataset, metric, baseline, and conditions without deciding what they imply. For code inventory, require repository-relative paths and line numbers when available.

Integrate and verify

Treat every delegate packet as an untrusted evidence bundle.

  1. Check that the lane stayed in evidence-collection scope and satisfied the schema.
  2. Map material observations to direct provenance.
  3. Deduplicate overlaps and identify disagreements.
  4. Resolve conflicts using direct evidence, source authority, reproducibility, and task-wide constraints.
  5. Independently verify pivotal, disputed, high-impact, or high-stakes claims.
  6. Separate observed facts, delegate interpretation, and primary-agent inference.
  7. Perform all deep reasoning and synthesize one coherent result; never concatenate packets as the final answer.

The primary agent owns hypotheses, root-cause analysis, recommendations, architecture, security judgment, final conclusions, user communication, implementation, validation, and every consequential action.

Guardrails

  • Respect higher-priority instructions, repository guidance, confidentiality, tool policies, and user constraints.
  • Do not expose sensitive context to a delegate that does not need it.
  • Do not create recursive agent trees or duplicate completed work.
  • Do not ask Luna to edit code or files, make external changes, choose an architecture, decide a root cause, perform a security assessment, or validate a high-stakes conclusion.
  • Do not delegate material requiring sustained global reasoning merely because it contains multiple files or sources.
  • Increase primary-agent verification for medical, legal, financial, security-sensitive, production, or irreversible evidence.
  • If Luna or subagent tooling is unavailable, say so briefly and collect the evidence directly using the same schema.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.