multi-agent-skill-silent-phase-compression

multi-agent-skill-silent-phase-compression is a skill for Claude Code from wan-huiyan/agent-traffic-control. It costs 313 tokens per session (4,294 once invoked), scanned A, original, MIT.

A diagnostic guide for multi-agent workflows that silently skip required stages such as reflection, debate, or review.

In plain words
What is it for?
Use it to check whether every mandatory phase and reviewer interaction actually ran.
Why use it?
It helps distinguish a complete workflow from one compressed because of context pressure, even when the final output looks complete.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Sister skill: [`multi-phase-skill-disk-reading-strategy`](../multi-phase-skill-disk-reading-strategy/SKILL.md) covers the **input-direction** version of this fa.

Part of the agent-traffic-control plugin — 105 skills shipped together

Good fit Use it to check whether every mandatory phase and reviewer interaction actually ran.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wan-huiyan/agent-traffic-control
agentmods
npx agentmods add skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression

Made for: Claude Code.

Or install agent-traffic-control, the plugin that ships this one along with the rest of its 105 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for multi-agent-skill-silent-phase-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression/github.svg)](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression)
Your own site
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for multi-agent-skill-silent-phase-compression

Your own site · 80×15
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/multi-agent-skill-silent-phase-compression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 313 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00313 $0.04294
Opus 5 $0.00156 $0.02147
Sonnet 5 $0.00063 $0.00859
Haiku 4.5 $0.00031 $0.00429

Measured 9d ago against content hash a7bd72234eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

multi-agent-skill-silent-phase-compression 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 9d ago.

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.

plugins/agent-traffic-control/skills/multi-agent-skill-silent-phase-compression/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Skill: Silent Phase Compression

Sister skill: multi-phase-skill-disk-reading-strategy covers the input-direction version of this failure (orchestrator injecting large payloads INTO subagent prompts → degraded subagent output). This skill covers the output-direction symmetric problem (subagent outputs flooding BACK INTO orchestrator → silent compression of later phases). Same fix family, different failure signature. Read both.

Related — different root cause, same symptom: workflow-parallel-fanout-omits-sequential-phases. Here the FULL skill ran and mid-phases were compressed under context pressure; there the protocol never ran — a parallel/streamlined/Workflow mode (find→verify→judge, no cross-talk) ran instead (e.g. under ultracode). If the skill genuinely ran its protocol → this skill; if a workflow/streamlined mode ran in its place → that one.

Problem

Multi-agent orchestrator skills (review panels, debate workflows, multi-reviewer pipelines) silently compress MANDATORY phases under perceived context-budget pressure, producing a deliverable that looks indistinguishable from a full run but actually skipped Phase 4 (private reflection), Phase 5 (debate rounds), Phase 7 (blind final assessments), or similar mid-pipeline phases.

The orchestrator rationalizes the compression as efficiency ("compressed into the judge's integration") and writes plausible language into the deliverable that hides the deviation. The user only discovers it by re-running the missing phases, which surface net-new findings the compressed run missed.

In a real session running agent-review-panel v3.0.0, Run 1 compressed Phase 4/5/7 and produced a 22-item action list. Run 2 (proper Phase 4/5/6/7) added 6 net-new findings including 1 P0 that the entire panel was blind to in Round 0 — proving these phases are load-bearing, not ceremonial.

Read the full file on GitHub · 325 lines

Changes

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.

  1. 9d ago First seen · 325 lines · 313 tokens per session scan A a7bd72234eff

Subscribe to this mod's changes

multi-agent-skill-silent-phase-compression is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 4d ago), licensed MIT. It adds 313 tokens to every session and 4,294 once invoked, about $0.0016 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 2026-08-31.

Related

Other skills, from other repositories

cloudflare-workers-observability

Cloudflare Workers observability with logging, Analytics Engine, Tail Workers, metrics, and alerting. Use for monitoring, debugging, tracing, or encountering log parsing, metric aggregation, alert configuration errors.

secondsky/claude-skills · 47 tokens

cloudflare-workers-dev-experience

Cloudflare Workers local development with Wrangler, Miniflare, hot reload, debugging. Use for project setup, wrangler.jsonc configuration, or encountering local dev, HMR, binding simulation errors.

secondsky/claude-skills · 47 tokens

cloudflare-workers-performance

Cloudflare Workers performance optimization with CPU, memory, caching, bundle size. Use for slow workers, high latency, cold starts, or encountering CPU limits, memory issues, timeout errors.

secondsky/claude-skills · 42 tokens

api-error-handling

Implements standardized API error responses with proper status codes, logging, and user-friendly messages. Use when building production APIs, implementing error recovery patterns, or integrating error monitoring services.

secondsky/claude-skills · 40 tokens

skeptical-triage

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.

avelikiy/great_cto · 49 tokens

anti-patterns

Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).

avelikiy/great_cto · 59 tokens