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.
npx agentmods add agents/zyqzyq/unfour/checkpoint_refreshgit clone --depth 1 https://github.com/zyqzyq/UnfourWrote 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.
[](https://agentmods.dev/agents/zyqzyq/unfour/checkpoint_refresh)<a href="https://agentmods.dev/agents/zyqzyq/unfour/checkpoint_refresh"><img src="https://agentmods.dev/badge/agents/zyqzyq/unfour/checkpoint_refresh.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01171 |
| Opus 5 | $0.00000 | $0.00585 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
CHECKPOINT_REFRESH 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.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint Refresh
Use this procedure to refresh repository progress documents after several completed task batches or after significant cross-layer changes.
Read First
AGENTS.md
docs/agents/START_HERE.md
docs/agents/EXECUTION_PROTOCOL.md
Goal
Refresh the repository checkpoint based on the current codebase and real verification results.
Only update:
docs/agents/PROJECT_STATE.md
docs/agents/OPEN_ISSUES.md
docs/agents/NEXT_STEPS.md
Do not modify source code, configuration, dependencies, or other documentation.
Scan
Inspect the current repository state:
git status --short
git log --oneline -10
Review:
apps/*
packages/*
crates/*
docs/agents/*
docs/architecture/*
docs/ui/*
docs/engineering/*
Confirm:
- implemented capabilities
- partially implemented capabilities
- not-started capabilities
- resolved issues
- new observed issues
- placeholders and stubs
- frontend lint and test status
- Rust test status
- build output and bundle chunks
- feature flags
- package boundaries
- security gaps
Do not reuse stale checkpoint content without verifying it against the repository.
Verification
Run the commands that currently exist in the repository:
git status --short
pnpm run lint
pnpm run test
pnpm run build
cargo fmt --check
cargo test --workspace
cargo check --workspace
cargo check -p unfour --features ssh-native
If a command does not exist, record:
N/A
If a command cannot run in the current environment, record:
NOT RUN
Include the reason. Never report unexecuted checks as passing.
Update PROJECT_STATE.md
Refresh:
- scan metadata
- branch
- current commit
- working tree state
- tech stack
- current phase
- verified capabilities
- partially implemented items
- not-started items
- verification results
- known limitations
Use only current repository facts and real command results.
Update OPEN_ISSUES.md
Refresh the issue list:
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 First seen · 267 lines · 0 tokens per session scan A b3731b94fb98
CHECKPOINT_REFRESH is an agent published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,171 tokens. 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.
Other agents, from other repositories
altai-implementer
Implements one bounded ALTAI roadmap slice and its tests. Default working agent for roadmap PRs.
altai-explorer
Read-only ALTAI repository exploration. Use when file ownership or existing patterns are unclear before implementing a roadmap item.
altai-reviewer
Read-only diff review for a risky ALTAI PR. Reports actionable findings only.
altai-test-triage
Triages failing tests/logs into product defects, flaky tests, environment problems, and pre-existing failures.
Test Engineer
Writes tests first, then implementation. Strict TDD.
researcher
Sample subagent that does focused research on a single question.