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.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/checkpointWrote 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/mishahanin/heading-os/checkpoint)<a href="https://agentmods.dev/skills/mishahanin/heading-os/checkpoint"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/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.
<a href="https://agentmods.dev/skills/mishahanin/heading-os/checkpoint"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 303 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.
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 | $0.00066 | $0.03458 |
| Opus 5.5 | $0.00026 | $0.01383 |
| Sonnet 5.5 | $0.00013 | $0.00692 |
| Haiku 4.5 | $0.00007 | $0.00346 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- checkpoint — 95% identical, 35 lines differ
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/checkpoint
Save a manual session checkpoint without running /compact or clearing context.
What this does
- Writes ONE combined handoff file to
outputs/operations/handoff-archive/ - Updates FOUR pointer files, all under the runtime store
runtime-junk/handoff/state/.latest/of the data root (not the archive directory, since 2026-09-14). This session's pair sits under.latest/{session-slug}/{summary.md,prompt.md}, which the SessionStart inject hook reads. The shared pair sits at.latest/{summary.md,prompt.md}, which/nextreads as "the newest handoff in this workspace" - Does NOT run
/compact - Does NOT clear the session
- Does NOT continue implementation after writing - wait for the user to direct next action
When to use
- Soft / hard checkpoint offer fired (
Stophook surfaced the context threshold) - About to switch to an unrelated task, want resume-ready snapshot
- Mid-implementation, want to save state before risky action
- Long session approaching natural pause point
Procedure
Step 0 - Handle a switch argument first
Split $ARGUMENTS on whitespace. If the FIRST token is exactly auto, exactly
unattended, or exactly compact-at, this is a switch. It is not a checkpoint.
Anything else is a note, including a word that merely begins with one of them.
Match the whole token, never a prefix. compact-at takes the SECOND token as its
value.
Run one of these, then stop. Do not write any file.
python scripts/checkpoint-paths.py --auto on
python scripts/checkpoint-paths.py --auto off
python scripts/checkpoint-paths.py --auto status
python scripts/checkpoint-paths.py --unattended on
python scripts/checkpoint-paths.py --unattended off
python scripts/checkpoint-paths.py --unattended status
python scripts/checkpoint-paths.py --compact-at 35
python scripts/checkpoint-paths.py --compact-at off
python scripts/checkpoint-paths.py --compact-at status
Report the command output in one line. For auto on, continue to Step 1 and
write the checkpoint as well. The operator asked at a threshold and expects this
one on disk. For unattended on, stop after the report. The operator is about to
leave, so a question here defeats the switch.
What ships with it
2 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.
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.
- 1mo ago Changed · +2 lines 558291c38ca7
- 1mo ago Changed · +1 lines 7a534dc093b7
- 1mo ago First seen · 308 lines · 66 tokens per session scan A a78b51bfe5b2
checkpoint is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,458 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
honcho
Configure and troubleshoot Honcho memory for Hermes.
unified-memory
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
pinecone-research
Agent RAG and long-term memory with Pinecone.
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
qmd
Hybrid local search over notes, docs, and transcripts.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.