forge-session

forge-session is a skill for Claude Code, Codex from ky2renzzz/acp-forge. It costs 31 tokens per session (230 once invoked), scanned A, original, MIT.

A tool for recording, checking, replaying, and comparing multi-agent execution sessions. It uses hashes, which are fingerprints of data, to detect changes in recorded events.

In plain words
What is it for?
It is for auditing agent activity, debugging failed runs by replaying them, verifying session files, and comparing two sessions to locate their first divergence.
Why use it?
It helps verify that a session was not altered and find the exact point where two runs began producing different results.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ky2renzzz/acp-forge/forge-session
Any agent
npx skills add ky2renzzz/acp-forge --skill forge-session
Clone the repo
git clone --depth 1 https://github.com/ky2renzzz/acp-forge

Made for: Claude Code, 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 forge-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/ky2renzzz/acp-forge/forge-session.svg)](https://agentmods.dev/skills/ky2renzzz/acp-forge/forge-session)
Your own site
<a href="https://agentmods.dev/skills/ky2renzzz/acp-forge/forge-session"><img src="https://agentmods.dev/badge/skills/ky2renzzz/acp-forge/forge-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00230
Opus 5 $0.00015 $0.00115
Sonnet 5 $0.00006 $0.00046
Haiku 4.5 $0.00003 $0.00023

Measured 5d ago against content hash c57a580bcbed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

forge-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 5d 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.

.grok/skills/forge-session/SKILL.md · 33 lines

What it actually says

Forge Session

Manage reproducible execution sessions.

Commands

List sessions

cargo run --manifest-path <path-to-acp-forge>/Cargo.toml -- session list

Verify session integrity

cargo run --manifest-path <path-to-acp-forge>/Cargo.toml -- session verify <path-to-session.json>

Checks every event's SHA-256 content hash and the session's integrity hash.

Diff two sessions

cargo run --manifest-path <path-to-acp-forge>/Cargo.toml -- session diff <session-a.json> <session-b.json>

Finds the first point where two sessions diverge.

Use Cases

  • Audit: verify that a recorded session was not tampered with
  • Debug: replay a failing session to find the exact divergence point
  • Compare: diff two runs of the same task to see what changed
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. 5d ago First seen · 33 lines · 31 tokens per session scan A c57a580bcbed

Subscribe to this mod's changes

forge-session is a skill published in the GitHub repository ky2renzzz/acp-forge (5 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 230 once invoked, about $0.0002 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

agent-communication-protocol

Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.

majiayu000/claude-skill-registry · 25 tokens

agent-communication-protocol

Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.

majiayu000/claude-skill-registry-data · 25 tokens

agent-communication-protocol

Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.

diegosouzapw/awesome-omni-skill · 25 tokens

sparc-methodology

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.

ruvnet/RuView · 29 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens