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 commands/thesmokedev/taskchad-os/image-node-prompt-packgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/commands/thesmokedev/taskchad-os/image-node-prompt-pack)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/image-node-prompt-pack"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/image-node-prompt-pack.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 5.1 | $0.00021 | $0.02411 |
| Opus 5 | $0.00010 | $0.01205 |
| Sonnet 5 | $0.00004 | $0.00482 |
| Haiku 4.5 | $0.00002 | $0.00241 |
Grade A, and why
image-node-prompt-pack 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 6d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Node Prompt Pack
Workflow ID: $WORKFLOW_ID
Contract
Build original, copy-safe prompts for Codex built-in image generation from the
selected library template. Do not render images in this node. Do not call OpenAI
APIs or CLI fallback scripts. Do not vendor or quote external prompt corpora. Use
the gpt-image-2-style-library skill as the structure and quality reference for
the chosen template_id and its example cases, then write your own prompts.
Read:
$ARTIFACTS_DIR/image-node-preflight.json$ARTIFACTS_DIR/image-node-brief.json$ARTIFACTS_DIR/image-node-selection.json$ARTIFACTS_DIR/image-node-grounding.local.json(written by thegroundnode)- Upstream preflight JSON:
$preflight.output - Upstream intake JSON:
$intake.output - Upstream selection JSON:
$select.output - Upstream grounding JSON:
$ground.output - The house discipline card at
.archon/image-nodes/$select.output.discipline_card.md, falling back to~/.archon/image-nodes/$select.output.discipline_card.mdwhen this workflow runs from a repository that does not carry its own cards.
Use:
image-node-grounding.local.jsonis the ONLY authoritative source of example cases. It carries real, checksum-verified case prompts for the resolvedexample_case_ids, retrieved offline from a pinned corpus. Read the exemplars for structure and quality, then write fresh prompt wording. Do not paste case text into the pack.- The installed skill's own
gallery.mdand case references are NON-AUTHORITATIVE. They are links to files that are not installed, and this node runs with web search disabled. Never resolve, follow, or quote them. If a case id is not in the grounding artifact, it does not exist for your purposes. - The skill's template blocks and taxonomy remain a valid structure reference.
Grounding and provenance:
- When
$ground.output.groundedistrue, stampprompt_engine,corpus_pin,corpus_source,corpus_sha256,license, and the RESOLVEDexample_case_ids(never the unresolved ones) into the prompt-pack JSON. - When it is
false, the retrieval matched nothing. Setself_authored: trueand OMITprompt_engineandexample_case_idsentirely. Never cite a source you did not read.
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.
- 6d ago First seen · 240 lines · 21 tokens per session scan A c1db81e941ae
image-node-prompt-pack is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 13d ago), licensed MIT. It adds 21 tokens to every session and 2,411 once invoked, about $0.0001 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
agent-brain-cache
View embedding cache metrics or clear the cache.
migrate_plans
Automatically review all plans in .cursor/plans/, determine relevance, and migrate relevant ones to docs/proposals/ for future consideration.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.
setup-dream
Configure Dream Mode for idle-time memory consolidation on this machine.