agent toolingby bilal140202
Agent Communication
bilal140202/agent-communication
AI DevKit · Exchange information with active Codex, Claude Code, and other AI agents using ai-devkit agent list, detail, and send.
What it changes
Passed 7 of 12 test cases with the skill, and 2 of 12 without it.
Without skill13%
With skill57%
Checks it passed that the model alone missed
- Uses `ai-devkit agent list --json`.
- Includes `ai-devkit agent list --json`.
- Uses `npx ai-devkit@latest agent list --json`.
and 12 more in the full report
11 fixed2 passed either way9 still failing1 broke
- Pass-rate lift
- +43 pp
- Tokens
- -49%
- Agent turns
- 0%
- Response time
- -62%
Model gemini-3.6-flashMeasured 8/8/2026v113 of 23 cases passed with skill · 12 comparable
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptShow the CLI invocation to retrieve the latest 50 context items from `security-guard` in machine-readable format.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Uses `ai-devkit agent detail --id security-guard --json --tail 50`. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 linessingle file
Agent Communication
Use ai-devkit agent ... to discover and communicate with active agents. If ai-devkit is not on PATH, use npx ai-devkit@latest agent ....
Commands
ai-devkit agent list --json
ai-devkit agent detail --id <agent-name> --json --tail 20
ai-devkit agent send --id <agent-name> "<message>"
ai-devkit agent send --id <agent-name> --wait --timeout 120000 --json "<message>"
<command> 2>&1 | ai-devkit agent send --id <agent-name> --stdin
Notes
list --json returns active agents with fields such as name, type, status, summary, projectPath, and lastActive.- Use the
name from list --json as --id. Partial matches are supported, but exact names are safer.
- Use
detail --json --tail <n> to read recent context from an agent before deciding what to send.
send --wait waits for a reply; add --json when the response should be machine-readable.send --stdin forwards piped command output or larger text.
Track record
Benchmark
7 / 12
test cases passed, vs 2 / 12 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks
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
Importedbilal140202 / the-lord-of-the-skills
skills/isengard/claude-code/codeaholicguy__ai-devkit/SKILL.md
License MITImported 8/2/2026Version v1