A checkpoint tool for saving the important state of a coding-agent conversation in a handoff document. The document lets a fresh session continue work without the full conversation history.

Use it to create a checkpoint, resolve an existing handoff reference, or check whether a saved projection is valid.

It reduces the chance of losing decisions, context, or unfinished work when a session ends or is handed to another agent.

wheypoint — Skill for Claude Code by paulnsorensen

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/paulnsorensen/easy-cheese

agentmods

npx agentmods add skills/paulnsorensen/easy-cheese/wheypoint

Made for: Claude Code.

Or install easy-cheese, the plugin that ships this one along with the rest of its 18 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/wheypoint/github.svg)](https://agentmods.dev/skills/paulnsorensen/easy-cheese/wheypoint)

Your own site

<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/wheypoint"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/wheypoint/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/wheypoint"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/wheypoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,635 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026
Socket pass 6 Sept 2026
Snyk pass 6 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Memory Poisoning · line 8
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00116	$0.01635
Opus 5	$0.00058	$0.00817
Sonnet 5	$0.00023	$0.00327
Haiku 4.5	$0.00012	$0.00163

Measured 3d ago against content hash 6bfc3d79cc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wheypoint 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 3d 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/wheypoint/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wheypoint

/wheypoint records the state a new agent needs to resume the work.

Use it for culture sessions, for work without a phase slug, and when a phase offers Checkpoint & stop.

Inputs

The conversation is the primary input.
The optional argument names the next session's focus.
The focus shapes the orientation line only.
The focus never removes a decision, question, blocker, or directive.

Runtime commands

Run every command through this skill's archive by its repository path; see ../cheese/references/harness-portability.md.

python3 skills/wheypoint/scripts/wheypoint.pyz turns [--session <id> | --transcript <path>]
python3 skills/wheypoint/scripts/wheypoint.pyz show --work-id <id>
python3 skills/wheypoint/scripts/wheypoint.pyz validate < intent.json
python3 skills/wheypoint/scripts/wheypoint.pyz checkpoint [--compacted <proof.json>] < intent.json
python3 skills/wheypoint/scripts/wheypoint.pyz schema checkpoint-intent
python3 skills/wheypoint/scripts/wheypoint.pyz resolve --ref <absolute-path | work-id | slug>
python3 skills/wheypoint/scripts/wheypoint.pyz lint <projection-path>
python3 skills/wheypoint/scripts/wheypoint.pyz list
python3 skills/wheypoint/scripts/wheypoint.pyz log --work-id <id>

resolve, lint, list, log, show, schema, and turns only read; direct invocations return output, and STOP before checkpoint writing.

/cheese --continue uses resolve and never invokes another archive; slash commands are host renderings, not the control model.

See references/commands.md for the generated command list.

Flow

Read the user's words. Run turns and keep every user turn in view.
Map each turn to an entry, or write one line that says why the turn is not captured.
Rehydrate. Run show for the work id; a first checkpoint binds the genesis sentinel itself.
After a compaction, rehydrate first and pass a proof with --compacted.
Write the intent. Follow references/intent-contract.md.
Put each user-stated constraint or preference in a directive entry with its verbatim quote.
Put each choice in a decision entry with a rationale.
Put each open item in a question or blocker entry.
Record a parked fork in decision_dossier with its options, evidence, and prior leaning.
Put the report a cold reader needs in notes.
Put paths and URLs in artifact_links and working_context, not their contents.
Validate. Run validate and fix every named problem.
Checkpoint. Run checkpoint.
Report. State the durability the result reports and the resume commands.

Read the full file on GitHub · 130 lines

Files

What ships with it

6 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.

3d ago Changed · -83 lines · -43 tokens per session 6bfc3d79cc7f
5d ago Changed · +2 lines 98db781431e7
10d ago First seen · 211 lines · 159 tokens per session scan A 1c21b33dd0b5

Subscribe to this mod's changes

wheypoint is a skill published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,635 once invoked, about $0.0006 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 2026-08-30.

Claude Code Code review Documents agent-skills ai-coding developer-tools

ring:creating-handoffs

Creating a handoff document that captures session state (completed work, decisions, open items, next steps) and delivering it via Plan Mode so the user gets the native 'clear context and continue implementing' resume option. Use when ending a session, when context grows large, or the user says 'handoff', 'save…

LerianStudio/ring · 93 tokens

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…

Gentleman-Programming/gentle-ai · 106 tokens

wheypoint