What is arch-explain-session?

A guide for explaining what happened during an agent session in ordinary language. An agent session is one run of an AI system, including its messages, tool calls, handoffs, and decisions.

Use it to inspect past or live sessions, find failures, trace events, and diagnose errors, tool failures, loops, handoffs, and guardrail decisions.

Agent logs often contain platform-specific details that make it hard to see why an agent failed, looped, missed input, or stopped. This turns the evidence into a checkable explanation.

arch-explain-session — Skill for Codex by Koredotcom/agents-mcp-tools

Install

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.

Any agent

npx skills add Koredotcom/agents-mcp-tools --skill arch-explain-session

Clone the repo

git clone --depth 1 https://github.com/Koredotcom/agents-mcp-tools

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-explain-session/github.svg)](https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-explain-session)

Your own site

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-explain-session"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-explain-session/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-explain-session"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-explain-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,547 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.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.01547
Opus 5.5	$0.00042	$0.00619
Sonnet 5.5	$0.00021	$0.00309
Haiku 4.5	$0.00010	$0.00155

Measured 1mo ago against content hash 5b9ca5e65e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-explain-session 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 1mo 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.

skills/arch-explain-session/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explain a session

A vague request ("analyze this trace") tempts a three-sentence answer in platform jargon. Developers cannot act on that, so they go back to the UI. This skill always returns the same checkable shape.

Gather the evidence

For any session that is not live in this MCP connection, pass projectId and source: "historical" on every debug_* read below; the default live source reads only local buffers and returns nothing for past sessions.

platform_connect, then confirm the project ID (required for history reads) and session ID. Find sessions with debug_session_history (action: "list"; agentName, channel and status take arrays; also outcome, range such as "7d", and sortBy: "errorCount" | "tokenCount" | "estimatedCost").
debug_analyze_session first: event counts, duration, model calls, current state, detected loops, errors, constraint violations and tool failures.
debug_traces to search instead of scrolling: filter by types, text or hasError, and on historical reads also by turnId, requestId, traceId or failureCode (agentName filters live reads only). Voice sessions add event types such as voice_dead_air, voice_filler_playback and voice_playback_watchdog. Live reads cut each value to about 200 characters; historical reads leave out the LLM prompt, messages and tool list (marked llmPayloadOmitted). For the full model request, ask the developer to use "Export entire trace" on the session page.
debug_explain_decision with turn or type (handoff, completion, gather_extraction) for why the agent chose what it chose.
debug_get_span_tree for execution order and timing; debug_get_current_state for gathered fields and the active flow step of a live session.
debug_get_flow_graph (after debug_load_agent, or with projectId, sessionId and source: "historical") (Mermaid) when you need to compare what happened with what the ABL says should happen.
For a transcript plus exported package, debug_why_transcript_failed maps symptoms to ABL file and line.

Read the full file on GitHub · 109 lines

Files

What ships with it

4 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.

1mo ago First seen · 109 lines · 104 tokens per session scan A 5b9ca5e65e6f

Subscribe to this mod's changes

arch-explain-session is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,547 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-09.

Building agents Debugging

arch-explain-session next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arch-explain-sessionKoredotcom/agents-mcp-tools	Skill	4	1mo ago	MIT	A	104	Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	326	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex
triaging-web-analytics-supportPostHog/posthog	Skill	41k	today	none	A	151	Claude Code, Codex