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-reportgit 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-report)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/image-node-report"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/image-node-report.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 | $0.00012 | $0.00600 |
| Opus 5 | $0.00006 | $0.00300 |
| Sonnet 5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
image-node-report 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Node Final Report
Workflow ID: $WORKFLOW_ID
Contract
Create the final local report for the workflow run. Do not render images in this node. Do not deploy, publish, submit to a marketplace, call OpenAI APIs, or use private paths.
Read:
$ARTIFACTS_DIR/image-node-preflight.json$ARTIFACTS_DIR/image-node-brief.json$ARTIFACTS_DIR/image-node-selection.json$ARTIFACTS_DIR/image-node-prompt-pack.md$ARTIFACTS_DIR/image-node-prompt-pack.json$ARTIFACTS_DIR/image-node-imagegen-packet.json$ARTIFACTS_DIR/images/manifest.json$ARTIFACTS_DIR/qa-report.md- Upstream QA JSON:
$qa.output - Upstream render JSON if present:
$render.output
Write:
$ARTIFACTS_DIR/image-node-final-report.md
Report Shape
Use markdown with these sections:
# Image Node Factory Report
## Verdict
## What Was Produced
## Selected Template And Discipline Card
## Style Library Attribution
State whether the run was GROUNDED. If `$ground.output.grounded` is `true`, name
the corpus pin, the source repository, the license, and the resolved case ids that
were actually read. If it is `false`, say plainly that no library case matched and
that the prompts are self-authored. Never attribute a library the run did not read.
Never quote case text, and never reference any `*.local.json` path.
## Render Mode And Status
## Artifact Paths
## QA Notes
## Local Test Commands
## Marketplace Readiness Notes
Rules:
- Make clear that this was a local run only.
- Name the selected
template_id, the librarycategory, the bounddiscipline_card, and theexample_case_idsthe selection used. Credit the awesome-gpt-image-2 style library as the prompt engine. - Confirm the pack carries both a baked and an overlay variant, and state which
render_modewas selected. - If render was skipped, say
render=falsedry-run and point to the prompt pack, packet, and manifest. - If render was blocked, say the pack was produced and the host did not expose Codex imagegen.
- If render succeeded, list the saved image paths and the rendered variant.
- Include a rerun command for prompt-pack-only mode and one for render mode.
- Do not say the workflow is submitted, published, deployed, or live.
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 · 82 lines · 12 tokens per session scan A 19ae9389025e
image-node-report is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 600 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.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.
value-propositions
Complete reference for managing the project's value propositions.
export-project
Export a single registered Gnosys project to a portable .json.gz bundle (round-trips with gnosys import project).