Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/matteocervelli/llms/recursive-communicatornpx skills add matteocervelli/llms --skill recursive-communicatorgit clone --depth 1 https://github.com/matteocervelli/llmsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.04430 |
| Opus 5 | $0.00015 | $0.02215 |
| Sonnet 5 | $0.00006 | $0.00886 |
| Haiku 4.5 | $0.00003 | $0.00443 |
Grade A, and why
recursive-communicator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The recursive-communicator skill provides structured protocols for managing recursive communication loops between the validation orchestrator, validation specialists, and the main feature implementer agent. It handles failure notifications, fix requests, re-validation triggers, and loop termination to ensure validation issues are resolved systematically.
When to Use
This skill auto-activates when you:
- Communicate validation failures to the main agent
- Request fixes from the main agent for validation issues
- Trigger re-validation after main agent fixes
- Manage recursive fix loops (failure → fix → re-check → repeat)
- Track iteration counts in recursive communication
- Prevent deadlocks in recursive loops
- Escalate unresolvable validation issues
- Log communication history for traceability
Provided Capabilities
1. Failure Communication
- Structured Failure Reports: Format validation failures for main agent
- Detailed Error Information: Include file locations, line numbers, error messages
- Suggested Fixes: Provide specialist recommendations for resolving issues
- Priority Tagging: Mark critical vs. non-critical failures
- Context Preservation: Include all relevant context for debugging
2. Fix Request Management
- Clear Fix Requests: Explicitly request main agent to fix specific issues
- Action Items: Provide actionable list of fixes needed
- Deadline Awareness: Track iteration limits (max 5)
- Fix Verification: Confirm when main agent completes fixes
- Re-validation Triggering: Signal specialists to re-check after fixes
3. Re-validation Coordination
- Re-check Signals: Trigger specialist re-validation after fixes
- Iteration Tracking: Increment and track iteration counts
- Status Updates: Communicate re-validation status to all parties
- Loop Continuation: Determine if another iteration needed
- Loop Termination: Identify when to exit recursive loop
4. Deadlock Prevention
- Max Iteration Limits: Enforce maximum 5 iterations per specialist
- Timeout Detection: Identify stalled communication
- Escalation Triggers: Escalate after max iterations or timeout
- User Intervention Requests: Flag when human input needed
- Graceful Degradation: Handle unresolvable issues without blocking workflow
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 635 lines · 29 tokens per session scan A 9c79a7ce5864
recursive-communicator is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 4,430 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…