slope-loop-guide

slope-loop-guide is a skill for Claude Code, Codex from srbryers/slope. It costs 107 tokens per session (1,018 once invoked), scanned A, original, MIT.

A guide to Slope, an automated development workflow that organizes coding work into sprints, checks progress, and records results. It also documents the project's tools, scoring system, and recovery procedures.

In plain words
What is it for?
Use it when running or reviewing automated sprints, checking loop status, investigating model-tier performance, or contributing to Slope's TypeScript monorepo, a repository containing multiple related packages.
Why use it?
It gives agents a shared process for starting sprints, handling hazards, reviewing outcomes, and recovering when the workflow encounters problems.

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/srbryers/slope/slope-loop-guide
Any agent
npx skills add srbryers/slope --skill slope-loop-guide
Clone the repo
git clone --depth 1 https://github.com/srbryers/slope

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 slope-loop-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/srbryers/slope/slope-loop-guide.svg)](https://agentmods.dev/skills/srbryers/slope/slope-loop-guide)
Your own site
<a href="https://agentmods.dev/skills/srbryers/slope/slope-loop-guide"><img src="https://agentmods.dev/badge/skills/srbryers/slope/slope-loop-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 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 $0.00107 $0.01018
Opus 5 $0.00053 $0.00509
Sonnet 5 $0.00021 $0.00204
Haiku 4.5 $0.00011 $0.00102

Measured 4d ago against content hash bbb3f2c2bd21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slope-loop-guide 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/synthesize.sh), 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.

slope-loop/slope-loop-guide/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slope Loop — Agent Guide

Auto-injected into every automated sprint via Aider's --read flag. Supplements (does NOT replace) CLAUDE.md, .claude/rules/, or .claude/hooks/.

File Map

File Purpose
SKILL.md This file — overview, execution protocol, quick reference
gotchas.md Loop-specific hazards with prevention steps
references/model-tier-rules.md Club-to-model mapping, escalation triggers, token thresholds
references/error-recovery.md Troubleshooting guide for all loop error scenarios
references/sprint-history.md Per-sprint learning archive (stub — populated by loop automation after each sprint)
scripts/synthesize.sh Compacts SKILL.md when it exceeds 5000 words

Project Quick Reference

  • SLOPE: Sprint Lifecycle & Operational Performance Engine
  • Package: @slope-dev/slope (v1.31.0+)
  • TypeScript monorepo, pnpm, vitest for tests, strict TypeScript
  • 46 CLI commands, SQLite store, MCP server, 28 guard hooks
  • Scoring: golf metaphors (handicap, par, birdie, bogey, hazards)

Sprint Execution Protocol (Loop Context)

  1. Pre-sprint: slope briefing shows hazards and nutrition trends
  2. Claim work: slope claim --target=<id> to claim a ticket or area
  3. Focused changes: Make minimal, targeted edits per ticket
  4. Validation: Run pnpm test and pnpm typecheck before committing
  5. Commit: Message format: <ticket-id>: <description>
  6. Release: slope release --target=<id> to release the claim
  7. Post-sprint: slope auto-card --sprint=<id> generates scorecard from git + CI signals
  8. Review: slope review formats the sprint review

Note: Use slope loop CLI commands — do not invoke shell scripts directly.

Model Tier Rules (Summary)

Club Model Escalation
Putter/Wedge Local (configurable)
Short Iron Local (configurable) Escalate on failure
Long Iron/Driver API (configurable)
Multi-file (2+) API (always)
>24K tokens API (always)

Read the full file on GitHub · 91 lines

Files

What ships with it

5 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. 4d ago First seen · 91 lines · 107 tokens per session scan A bbb3f2c2bd21

Subscribe to this mod's changes

slope-loop-guide is a skill published in the GitHub repository srbryers/slope (6 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,018 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 2026-08-31.

Related

Other skills, from other repositories

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

pm-all

Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).

wei63w/pm-manager · 8 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens

simulator-reactions

Simulator.Company reactions specialist — comments, events, approvals, ratings and other feedback attached under an actor. Use when the user wants to comment on an actor, reply in a thread, read/like/pin the discussion, mark comments read, or get reaction stats. Activate when the user says "comment on this actor"…

corezoid/simulator-ai-plugin · 174 tokens

glab-issue

Create, view, update, and manage GitLab issues. Use when working with issue tracking, bug reports, feature requests, or task management. Operations include creating issues, listing with filters, viewing details, adding comments/notes, updating labels/assignees/milestones, closing/reopening, and board management.…

vince-winkintel/gitlab-cli-skills · 89 tokens