agentmods.dev

interlateral_agents: Skill for Claude Code

.agent/skills/sprint-overseer/SKILL.md

sprint-overseer is a skill for Claude Code, Codex from dazzaji/interlateral_agents. It costs 40 tokens per session (3,727 once invoked), scanned A, original, Apache-2.0.

A monitoring skill for a software sprint, a planned period of development work. It checks the manager and worker sessions against a sprint specification, records progress, and intervenes only when work is genuinely stuck.

In plain words
What is it for?
It is for observing agent sessions, classifying sprint progress, nudging stalled workers, and appending completion or checkpoint logs.
Why use it?
It gives teams a repeatable way to notice stalled work and preserve a written checkpoint without taking over the sprint.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

This is dazzaji/interlateral_agents's own configuration. It tells Claude Code and Codex how to work on interlateral_agents 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 interlateral_agents configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/dazza/repos/project/docs/sprint.md.

not rated 11repo 10d ago A scan 40 tokens original Apache-2.0
View source ↗ dazzaji/interlateral_agents
Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. 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/dazzaji/interlateral_agents/main/.agent/skills/sprint-overseer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dazzaji/interlateral_agents

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 sprint-overseer

README.md
[![agentmods](https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/sprint-overseer/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/sprint-overseer)
Your own site
<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/sprint-overseer"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/sprint-overseer/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 sprint-overseer

Your own site · 80×15
<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/sprint-overseer"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/sprint-overseer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,727 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 $0.00040 $0.03727
Opus 5.5 $0.00016 $0.01491
Sonnet 5.5 $0.00008 $0.00745
Haiku 4.5 $0.00004 $0.00373

Measured 1mo ago against content hash e3b7739abdd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sprint-overseer 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.

.agent/skills/sprint-overseer/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Overseer

Purpose

You are a sprint overseer. Your job is to periodically check on another agent running a sprint, determine whether the sprint is on track, and log that judgment.

You do not execute the sprint yourself. You observe, classify, and intervene only when needed.

Default roster: use Claude Code and Codex overseers. Do not assign Gemini CLI, Antigravity CLI, or Antigravity Desktop as overseers unless the human prompt explicitly names that peer.

Inputs

All inputs come from the prompt.

Required:

  • sprint_file: absolute path to the sprint specification file

Optional:

  • manager_session: tmux session name for the sprint lead. Default: ia-claude
  • poll_interval: human-readable cadence for the mechanical wake-ups. Default: every 5 minutes
  • done_marker: text that signals team completion in the team evidence file. Default: STATUS: DONE
  • sprint_team_pattern: tmux session glob for sprint workers. Default: sprint*
  • closeout_file: explicit absolute path to the team-completion artifact. Use this when the sprint does not use the default {sprint_dir}/evidence/sprint_closeout.md.
  • stop_file: explicit absolute path to the overseer-completion artifact. Use this when the timer should continue after team completion until the overseers write their own final closeout.
  • stop_marker: text that signals overseer completion in stop_file. Default: same as done_marker

Derived Paths

Derive these from sprint_file every time:

  • sprint directory: parent of sprint_file
  • overseer log: {sprint_dir}/sprint-overseer-log.md
  • evidence directory: {sprint_dir}/evidence/
  • team evidence file: {closeout_file} if provided, otherwise {sprint_dir}/evidence/sprint_closeout.md
  • overseer stop file: {stop_file} if provided, otherwise the same path as the team evidence file

Do not hardcode repo-specific paths.

First Activation

  1. Read the sprint file fully enough to understand phases, gates, and completion criteria.
  2. Create the overseer log if it does not exist with this header:

Read the full file on GitHub · 317 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. 1mo ago First seen · 317 lines · 40 tokens per session scan A e3b7739abdd9

Subscribe to this mod's changes

sprint-overseer is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 40 tokens to every session and 3,727 once invoked, about $0.0002 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 2026-10-03.

PlanningProject management
Related

sprint-overseer compared with skills from other repositories

sprint-overseer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sprint-overseerdazzaji/interlateral_agentsSkill1110d agoApache-2.0A40Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code