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/jovesun-lab/arcgram/checkpointnpx skills add jovesun-lab/arcgram --skill checkpointgit clone --depth 1 https://github.com/jovesun-lab/arcgramWrote 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/jovesun-lab/arcgram/checkpoint)<a href="https://agentmods.dev/skills/jovesun-lab/arcgram/checkpoint"><img src="https://agentmods.dev/badge/skills/jovesun-lab/arcgram/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 | $0.00103 | $0.00903 |
| Opus 5 | $0.00051 | $0.00451 |
| Sonnet 5 | $0.00021 | $0.00181 |
| Haiku 4.5 | $0.00010 | $0.00090 |
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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint - Arcgram logic self-check validator
One input: a diagram (treated as a spec). One question: is the flow logic well-formed and coherent? Returns typed findings; marks, never blocks.
Sibling to Reconcile: Checkpoint checks structure from the diagram alone; Reconcile checks values across diagram + code. Run both -> the diagram is a faithful, current spec.
It checks the graph's logic structure - not drawing quality (the engine auto-handles overlaps/spacing/routing) and not semantic correctness (whether the logic is right - a human call).
Red line: reads only the semantic field values id, f, t, kind, role, type
(plus optional status, flag). Never a coordinate, color, size, or spacing. The judge: am I
reading a semantic string, or a rendered visual quantity?
Findings
Tier A - structural integrity (always on). Domain-agnostic graph theory.
| finding | means |
|---|---|
dangling-edge |
an edge points at an id that is not a node |
orphan-node |
a node has no edge (chain broken) - except a declared type:'open' |
missing-branch |
a decision (kind:'diamond') lacks its Y or N branch |
disconnected-island |
a cluster with no edge to the main flow |
duplicate-id |
a node id used more than once |
missing-field |
a node has no id, or an edge no f/t |
missing-meta-version |
ARCGRAM_META.version absent |
empty-diagram |
no nodes - reported uncovered, never falsely "clean" |
Tier B - justification coherence (auto-on for a thinking flow). Does it read as reasoning:
every action traces back to a goal, every goal reaches an action, every decision sits
on a justification path. Auto-on when the diagram has a decision diamond (kind:'diamond', = the
engine's _isThinkflow); no-diamond diagrams skip it. Override --tier-b / --no-tier-b. Roles:
goal/action/decision (coherence-bearing) + constraint/evidence/state/output
(recognized). No resolvable role -> [?] uncovered, never guessed. cat is not read.
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.
- 4d ago First seen · 78 lines · 103 tokens per session scan A 9609bb1f6dff
checkpoint is a skill published in the GitHub repository jovesun-lab/arcgram (9 stars, last pushed 16d ago), licensed Apache-2.0. It adds 103 tokens to every session and 903 once invoked, about $0.0005 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
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
panel-node-pack-sync
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (installcomfyui (action:"selfupdate"), npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way…
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…