FylloCode: Skill for Codex

.agents/skills/adapt-acp-events/SKILL.md

adapt-acp-events is a skill for Codex from Fioooooooo/FylloCode. It costs 95 tokens per session (2,926 once invoked), scanned A, original, MIT.

A development skill for translating ACP agent session events into the event format used by FylloCode. ACP is a protocol for exchanging messages and tool activity between coding agents and host applications.

In plain words
What is it for?
Use it when adding an ACP agent, fixing how its tool activity or titles appear, examining ACP traces, or updating an event adapter and its tests.
Why use it?
Different agents may describe tool calls and updates differently, which can cause missing or unclear activity in the user interface. This skill helps make the smallest compatibility change supported by real event data.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is Fioooooooo/FylloCode's own configuration. It tells Codex how to work on FylloCode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FylloCode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Fioooooooo/FylloCode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Fioooooooo/FylloCode/main/.agents/skills/adapt-acp-events/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Fioooooooo/FylloCode

Made for: Codex.

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 adapt-acp-events

README.md
[![agentmods](https://agentmods.dev/badge/skills/fioooooooo/fyllocode/adapt-acp-events/github.svg)](https://agentmods.dev/skills/fioooooooo/fyllocode/adapt-acp-events)
Your own site
<a href="https://agentmods.dev/skills/fioooooooo/fyllocode/adapt-acp-events"><img src="https://agentmods.dev/badge/skills/fioooooooo/fyllocode/adapt-acp-events/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 adapt-acp-events

Your own site · 80×15
<a href="https://agentmods.dev/skills/fioooooooo/fyllocode/adapt-acp-events"><img src="https://agentmods.dev/badge/skills/fioooooooo/fyllocode/adapt-acp-events.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,926 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 81
    Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.
    Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
How audits are shown
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 $0.00095 $0.02926
Opus 5 $0.00048 $0.01463
Sonnet 5 $0.00019 $0.00585
Haiku 4.5 $0.00010 $0.00293

Measured 9d ago against content hash 0de00aa37636, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adapt-acp-events 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze-acp-session-updates.mjs, scripts/capture-acp-events.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/adapt-acp-events/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adapt ACP Events

Turn real ACP traces into the narrowest evidence-backed compatibility change while preserving FylloCode's stable internal event semantics.

Read Before Acting

  1. Read the repository AGENTS.md and inspect git status --short.
  2. Read these files in full before changing covered areas:
    • guidelines/Architecture.md
    • guidelines/MainProcess.md
    • guidelines/Testing.md
    • guidelines/QualityGates.md
    • openspec/specs/acp-tool-event-fidelity/spec.md
  3. Read the current mapper, normalizers, adapter types and registry, relevant adapters, SessionEvent, MessageAssembler, shared tool-call assembly, and their tests. Treat current source and specs as authoritative; do not rely on paths or field behavior remembered from an earlier run.
  4. Read adaptation-decision-matrix.md in full.

Establish the Adaptation Boundary

State whether the request is:

  • new integration: add evidence and the narrowest adapter support for an Agent not yet optimized; or
  • existing integration optimization: reproduce and correct a known mapping or display mismatch.

Record the canonical agentId, display name, actual running version, version source, ACP SDK version, and underlying Agent version when a bridge or adapter is involved. Prefer a detected or command-reported version over a registry latest version. Use null with agentVersionSource: "unavailable" when the actual version cannot be established; never silently omit it or substitute latestVersion.

Do not execute an arbitrary custom Agent with --version. Use already available status, package, registry, or user-provided evidence. If version discovery would launch unknown code or mutate state, ask first.

Capture Real Evidence

Capture representative session/update sequences, not isolated screenshots or normalized output. Build a version-scoped tool inventory before sampling instead of assuming standardized tool names:

  1. Discover the complete tool set exposed by the target Agent/version from authoritative, non-mutating sources available for that Agent, such as its tool listing or help surface, registry/configuration, session capabilities, and prior raw traces. Include dynamically provided MCP, skill, mode-specific, and subagent tools when they are available.
  2. Preserve each exact raw tool name or identifier and the source that proved its availability before applying any semantic normalization. Do not collapse Agent-specific names into generic categories during evidence collection.
  3. Attempt at least one safe representative invocation for every discovered tool. Exercise conditional tools by entering their required mode or configuration when that is safe and already authorized.
  4. Keep a coverage ledger in the versioned analysis document with the discovered tool, exact raw name or identifier, observed raw title variants, inventory source, sampled scenarios, observed update shapes, semantic family candidate, coverage status, and any skip or blocked reason.
  5. Use read, search, edit, execute, fetch, MCP, and subagent only as fallback semantic coverage dimensions for finding inventory gaps, never as an allowlist or a substitute for the Agent's actual tool inventory.

Read the full file on GitHub · 153 lines

Files

What ships with it

6 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.

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 · 153 lines · 95 tokens per session scan A 0de00aa37636

Subscribe to this mod's changes

adapt-acp-events is a skill published in the GitHub repository Fioooooooo/FylloCode (29 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 2,926 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

qa-testing

Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…

openinterpreter/openinterpreter · 77 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

ultra-adlc

End-to-end delivery orchestration for explicitly requested, very large software changes that must be completely implemented and independently proven. Use when the user invokes "ultra-adlc" or asks for an Ultra-ADLC-scale full delivery; do not use for ordinary features, small fixes, reviews, or ad hoc parallel work.

KonghaYao/peri · 69 tokens

go-127

What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…

dimetron/pi-go · 177 tokens

bubbletea-testing

Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…

dimetron/pi-go · 139 tokens

pi-loop-forensics

Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.

dimetron/pi-go · 65 tokens