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/postindustria-tech/agentic-toolkit/neograph-dev-checkpointnpx skills add postindustria-tech/agentic-toolkit --skill neograph-dev-checkpointgit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/neograph-dev-checkpoint)<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/neograph-dev-checkpoint"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/neograph-dev-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 | $0.00069 | $0.01119 |
| Opus 5 | $0.00034 | $0.00560 |
| Sonnet 5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
neograph-dev-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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neograph Checkpoint System
Schema-aware checkpoint resume that automatically detects what changed and re-executes only affected nodes. Based on the Prefect cache-miss model.
Schema Fingerprinting
Two fingerprint functions in state.py:
compute_schema_fingerprint(state_model) -- state.py:298
SHA-256 prefix (16 chars) of sorted (field_name, annotation_string) pairs.
Excludes framework fields (neo_*, node_id, project_root, human_feedback).
Changes when any field is added/removed or its type changes.
compute_node_fingerprints(construct) -- state.py:262
dict[str, str] mapping each node's state field name to a SHA-256 prefix (12 chars).
Hash input: "{field_name}:{type.__qualname__}".
For dict-form outputs (multi-output): one fingerprint per output key.
For sub-constructs: fingerprinted by their output type.
Compile-Time Attachment
compiler.py:204-205 stashes both fingerprints on the compiled graph:
compiled._neo_schema_fingerprint = compute_schema_fingerprint(state_model)
compiled._neo_node_fingerprints = compute_node_fingerprints(construct)
Run-Time Injection
runner.py:267-272 injects fingerprints into the initial state dict so they
persist in the checkpoint alongside node outputs.
Resume Flow
_verify_checkpoint_schema() in runner.py:74-127:
- Read stored
neo_schema_fingerprintfrom checkpoint channel_values - Compare against current
_neo_schema_fingerprinton the compiled graph - If match: resume normally
- If mismatch:
_compute_invalidated_nodes()diffs per-node fingerprintsauto_resume=True: call_auto_resume_from_divergence()auto_resume=False: raiseCheckpointSchemaError(invalidated_nodes=...)
Auto-Resume: The LangGraph Time-Travel Pattern
_auto_resume_from_divergence() in runner.py:129-154:
- Walk
graph.get_state_history(config)backwards (newest to oldest) - Find the snapshot where an invalidated node appears in
.next(meaning "this checkpoint was taken just before that node ran") - Extract
checkpoint_idfrom that snapshot's config - Mutate caller's
config["configurable"]["checkpoint_id"]in-place - Back in
run(),graph.invoke(None, config=config)resumes from rewind point - LangGraph naturally re-executes from the rewind point forward
What ships with it
1 file 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.
- 3d ago First seen · 125 lines · 69 tokens per session scan A a30fbf3e8a67
neograph-dev-checkpoint is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,119 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…