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 skills/svy04/ballast/checkpointnpx skills add svy04/ballast --skill checkpointgit clone --depth 1 https://github.com/svy04/ballastWrote 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/skills/svy04/ballast/checkpoint)<a href="https://agentmods.dev/skills/svy04/ballast/checkpoint"><img src="https://agentmods.dev/badge/skills/svy04/ballast/checkpoint.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 | $0.00071 | $0.00957 |
| Opus 5 | $0.00036 | $0.00478 |
| Sonnet 5 | $0.00014 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00096 |
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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint — return in thirty seconds
A session ends; the work doesn't. Whoever returns — the user after a week, or a fresh session after a context reset — faces scrollback that no longer exists and a directory that doesn't explain itself. Reconstruction eats the first twenty minutes and gets details wrong. This skill keeps one file that makes return instant, and a second file that carries orders across the gap without letting them go stale.
CHECKPOINT.md — the return point
Update memory/CHECKPOINT.md whenever a large unit of work completes or the session is winding down. Five sections, always in this order:
# Checkpoint — <goal> — <YYYY-MM-DD HH:MM>
## The story so far
<Thirty seconds of reading, no more. What this work is and where it
stands, told to someone with zero context.>
## Decided
<Decisions confirmed since the last checkpoint — one line each, with
ledger ids where they exist.>
## Waiting on the user
<Decisions only the user can make, and the readings in force from
OPEN-QUESTIONS that are due a question — one line each, so they get asked
here, at the break, not mid-flow. Empty is a valid and welcome state.>
## Next first action
<ONE line, executable immediately without reading anything else.>
## Tried
<Approaches attempted that did not work, one line each with why.>
Rules:
- Next first action is the load-bearing line. A cold session must be able to execute it before reading a single other file: concrete verb, concrete object, no prerequisite. "Continue the analysis" fails this test; "run the export script against the staging list and diff the counts" passes.
- Tried is a map of dead ends. An approach that failed and went unrecorded will be attempted again, in good faith, by a session that has no way to know better. One line per dead end — what was tried, why it didn't work.
- Archive on every update. Before overwriting, copy the outgoing version to
memory/checkpoints/{YYYYMMDD-HHMM}-<short-title>.md. That directory is append-only and sorts itself by filename — the full trail of how the work moved, at zero extra cost. - Index each file the first time it appears. When this skill first creates
memory/CHECKPOINT.md,memory/checkpoints/, ormemory/HANDOFF.md, add a row for it to the File map inmemory/00-INDEX.md— a file missing from the map is a file the next session never opens.
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.
- 5d ago First seen · 64 lines · 71 tokens per session scan A e351d800b0af
checkpoint is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 10d ago), licensed MIT. It adds 71 tokens to every session and 957 once invoked, about $0.0004 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.
Other skills, from other repositories
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).
smart-loader
Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.