checkpoint

A command that records the current coding session in a daily log, project notes, a Planner progress value, and a Pulse update.

In plain words
What is it for?
Use it at the end of a session to identify touched projects and save work summaries, progress, and updates in the listed locations.
Why use it?
It avoids copying the same session summary into several tracking systems. It asks for confirmation before writing anything.

Command

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 commands/codebloodedai/claude-code-ops-commands/checkpoint
Clone the repo
git clone --depth 1 https://github.com/codebloodedai/claude-code-ops-commands
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,774 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 $0.00026 $0.01774
Opus 5 $0.00013 $0.00887
Sonnet 5 $0.00005 $0.00355
Haiku 4.5 $0.00003 $0.00177

Measured yesterday against content hash 95bb69706900, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

commands/checkpoint.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

One-shot session save. Run this when you want to capture the state of the current session into all four places at once:

  1. ~/vault/daily/YYYY-MM-DD.md — daily log (always)
  2. ~/vault/projects/<project>.md — vault project notes (one per project touched)
  3. Planner — % complete via az rest PATCH
  4. Pulse — brief + history via authenticated PATCH

This is a meta-command that orchestrates the existing /planner-push and /pulse-update flows plus the vault/daily-log writes. Respects the same safety rules: nothing gets written without explicit confirmation.

Step 1: Detect projects touched in this session

Look at the conversation + recent file edits + git state to identify which projects were worked on. Signals:

  • Files edited under ~/Code/<repo>/ → that project is touched
  • Git commits created in this session → the repo's project is touched
  • Slash commands invoked (/myproject, /portal, etc.) → those projects are touched
  • Deploys that ran (func publish, swa deploy, gh run watch)
  • Vault notes updated
  • Azure CLI commands against a resource group that maps to a project

Build a set: { project_key: summary_of_work }. The project_key is the short slug (e.g., project-alpha, portal, hopper, cc). If in doubt, ask the user which projects to include. Don't guess wildly — if work spans ambiguous boundaries, ask.

Step 2: Show the detected scope + ask for confirmation

📦 Checkpoint scope (auto-detected):

  Project Alpha:
    - Fixed SWA linked-backend routing
    - Merged fix/csp-inline-handlers → main
    - Added DNS A record for Azure OpenAI PE
    - Backfilled references on all 4 records
    Signals: 5 commits in ~/Code/project-alpha, /project-alpha invoked,
             az rest against rg-project-alpha-prod, Playwright against SWA

  Process Portal:
    - Added CLAUDE.md stub
    Signals: 1 untracked file

Targets to update:
  [✓] ~/vault/daily/2026-04-09.md   (append session summary)
  [✓] ~/vault/projects/project-alpha.md (update state + risks + todos)
  [ ] ~/vault/projects/process-portal.md (skipping — CLAUDE.md only, no material change)
  [✓] Planner task: "Project Alpha" → 75 → 85
  [✓] Pulse brief: Project Alpha (actions, next steps, risks)

Proceed with all 4 writes? [y / edit scope / abort]

Read the full file on GitHub · 123 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. yesterday First seen · 123 lines · 26 tokens per session scan A 95bb69706900

Subscribe to this mod's changes

checkpoint is a command published in the GitHub repository codebloodedai/claude-code-ops-commands (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,774 once invoked, about $0.0001 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.