Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

A5c AI/Convoy Management — measured AI agent skill | DecimalAI

a5c-ai/convoy-management

SkillScore74Maintained

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull a5c-ai-convoy-management

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-convoy-management/SKILL.md

Raw file: /s/a5c-ai-convoy-management/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-convoy-management.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

Yes — +74% lift-38% tokens0% turns74% of whole cases pass with skill (17/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-51%	0%
case-02	✗→✓	▲ Improved	68%	0%
case-03	✗→✓	▲ Improved	-39%	0%
case-04	✗→✓	▲ Improved	-37%	0%
case-05	✗→✓	▲ Improved	-82%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/methodologies/gastown/skills/convoy-management/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Coordinating parallel bead execution across agents
Tracking progress of distributed work
Landing (merging) completed convoy results

Process

Create convoy from goal or MEOW decomposition
Decompose into beads (persistent) and wisps (ephemeral)
Assign beads to Crew (long-lived) or Polecats (transient)
Track progress via hooks and heartbeats
Verify all beads complete with quality checks
Land convoy by merging bead branches

Key Concepts

Convoy: Primary work-order wrapping related beads
Bead: Git-backed atomic work unit (issue/task)
Wisp: Ephemeral bead destroyed after successful run
GUPP: If there is work on your Hook, YOU MUST RUN IT

Agents Used

agents/mayor/ - Creates and coordinates convoys
agents/crew-lead/ - Persistent collaborator on beads
agents/polecat/ - Transient worker for individual beads

Tool Use

Invoke via babysitter process: methodologies/gastown/gastown-convoy

Want to see if a5c-ai/convoy-management would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.