goal-checkpoint

goal-checkpoint is a skill for Claude Code, Codex from jamesyang124/agent-skills. It costs 46 tokens per session (1,483 once invoked), scanned A, original, MIT.

A checkpoint and resume system for long coding tasks. It records the current goal and work state so a later session can continue when the conversation is nearly full.

In plain words
What is it for?
Use it at the start of a substantial task and when the context window is filling up. It saves a GOALSTATE.md file and commits a checkpoint of the current work.
Why use it?
It reduces the risk of losing progress when a task spans multiple sessions or files. A saved snapshot gives the next session enough context to pick up the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it at the start of a substantial task and when the context window is filling up. It saves a GOALSTATE.md file and commits a checkpoint of the current work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamesyang124/agent-skills/goal-checkpoint
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 jamesyang124/agent-skills --skill goal-checkpoint
Clone the repo
git clone --depth 1 https://github.com/jamesyang124/agent-skills

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 goal-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesyang124/agent-skills/goal-checkpoint/github.svg)](https://agentmods.dev/skills/jamesyang124/agent-skills/goal-checkpoint)
Your own site
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/goal-checkpoint"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/goal-checkpoint/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 goal-checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/goal-checkpoint"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/goal-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,483 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 $0.00046 $0.01483
Opus 5.5 $0.00018 $0.00593
Sonnet 5.5 $0.00009 $0.00297
Haiku 4.5 $0.00005 $0.00148

Measured 1mo ago against content hash 336cfc80563e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goal-checkpoint 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-settings/skills/workflows/goal-checkpoint/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Checkpoint

This skill provides structured goal tracking across sessions. When context fills up (~90%), it commits a checkpoint so the next session can resume exactly where this one left off.

When to Use

Invoke at the start of any non-trivial session where:

  • The task spans multiple steps or files
  • Work may not finish in one context window
  • A clean resume in the next session is important

Trigger phrase: "use goal-checkpoint for this" or "/goal-checkpoint"


Phase 1: Goal Declaration (Session Start)

When invoked, immediately:

1. Ask for the goal

Ask the user:

"Describe the goal for this session. What should be accomplished, and what does 'done' look like?"

2. Write GOAL_STATE.md

Create (or overwrite) GOAL_STATE.md in the repo root:

# Goal State

## Goal
[User's stated goal, verbatim]

## Done When
[User's definition of done]

## Started
[ISO date-time]

## Status
in-progress

## Steps
- [ ] [Step 1]
- [ ] [Step 2]
...

## Completed Steps
(none yet)

## Context Notes
(key decisions, blockers, environment state)

## Resume From
(filled in at checkpoint — what to do first in the next session)

3. Initial commit

Stage and commit GOAL_STATE.md:

chore(goal): 🎯 start session — [one-line goal summary]

Phase 2: Progress Tracking (During Session)

As work progresses:

  • After each significant step completes, move it from Steps to Completed Steps in GOAL_STATE.md and add a brief note.
  • After any file is substantially changed, note it under Context Notes with a one-line description of its current state.
  • Do not commit after every update — batch updates until a natural checkpoint.

Phase 3: Checkpoint Protocol (At ~90% Context)

When context approaches 90% (observed via system reminders about context compression, or when the conversation feels dense), trigger a checkpoint before responding to the next user message.

3.1 Assess current state

Before committing, determine:

  • Which steps are complete vs. in-progress
  • Which files have been modified and how
  • What the very next action should be in the next session
  • Any environment or tool state the next session needs to know

Read the full file on GitHub · 270 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 · 270 lines · 46 tokens per session scan A 336cfc80563e

Subscribe to this mod's changes

goal-checkpoint is a skill published in the GitHub repository jamesyang124/agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 1,483 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 2026-08-31.

Related

Other skills, from other repositories

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 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

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens