agentmods.dev

session-steward

session-steward is a skill for Claude Code, Codex from Justinmendezai/The-Adam-Repo. It costs 57 tokens per session (1,615 once invoked), scanned A, original, Apache-2.0.

A lightweight record-keeping workflow for an agent-run project. It summarizes the latest bounded work session into project files and refreshes the brief for the next session.

In plain words
What is it for?
Use it after a build session, acceptance test, or blocked cycle to record results and prepare the next agent brief. It does not change production code or dispatch other agents.
Why use it?
Long projects can lose important context between separate agent runs. Keeping the current state, completed work, tests, and open operator tasks in files makes handoffs clearer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 12repo +1 18d ago A scan 57 tokens original Apache-2.0

Good fit Use it after a build session, acceptance test, or blocked cycle to record results and prepare the next agent brief. It does not change production code or dispatch other agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justinmendezai/the-adam-repo/session-steward
View source ↗ Justinmendezai/The-Adam-Repo justinmendez.ai
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 Justinmendezai/The-Adam-Repo --skill session-steward
Clone the repo
git clone --depth 1 https://github.com/Justinmendezai/The-Adam-Repo

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 session-steward

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/session-steward/github.svg)](https://agentmods.dev/skills/justinmendezai/the-adam-repo/session-steward)
Your own site
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/session-steward"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/session-steward/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 session-steward

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/session-steward"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/session-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,615 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 $0.00057 $0.01615
Opus 5 $0.00028 $0.00807
Sonnet 5 $0.00011 $0.00323
Haiku 4.5 $0.00006 $0.00161

Measured 12d ago against content hash dd2646aac04b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

session-steward 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 12d 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/session-steward/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

session-steward

Meta orchestrator = memory manager, not implementer. Long-term continuity lives in agent-control/, orchestration-runs/, git, and tests — not in one endless chat.

Use this skill after a build orchestrator finishes a bounded cycle (or when the human asks for the next brief).

Explicit non-goals

  • No edits to production src/, app/, etc.
  • No dispatch-builder / dispatch-parallel.
  • No slice spec or test file changes.
  • Minimal reasoning: compress, file, link — do not replan the whole product.

When to use

  • A build orchestrator completed one objective in agent-control/active-sprint.md (or stopped with a clear blocker).
  • Token pressure: you want a fresh build orchestrator with a tight brief.
  • After e2e-acceptance or a major test pass — roll results into agent-control/test-status.md.

Inputs (read-only)

  • agent-control/active-sprint.md, agent-control/current-state.md, agent-control/completed-work.md
  • agent-control/slice-status.md — final registry state
  • agent-control/human-queue.md — open operator items
  • agent-control/rework-ledger.md — agentic review/rework rows this run (create empty template if missing)
  • Latest orchestration-runs/run-* folder (if any)
  • scratch/last-run.md, scratch/handoff/primer-*.md (most recent optional)
  • slices/README.md, plan/CONTEXT.md (one screen each)
  • scratch/e2e-acceptance.md or scratch/run-results/e2e-*.json if present
  • packet/PACKET.md verification / e2e for test layer names

Context budget (soft)

Output Target
next-orchestrator-brief.md ~20k–30k characters; bullets first
orchestration-runs/run-NNN/summary.md ~2k–4k characters
Bullet lists 10 bullets max for “what happened” and “what’s next”

Do not rely on live token meters — use character caps and short bullets.

Workflow

1. Allocate run id

  • Pick the next folder: orchestration-runs/run-003/ (zero-pad or use date — match existing convention in the repo).
  • If the build orchestrator already created this folder and filled files, update in place instead of duplicating.

Read the full file on GitHub · 103 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. 12d ago First seen · 103 lines · 57 tokens per session scan A dd2646aac04b

Subscribe to this mod's changes

session-steward is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,615 once invoked, about $0.0003 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.

Building agentsProductivity
Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens