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-qagit 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-qa)<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/image-node-qa"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/image-node-qa.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 | $0.00011 | $0.01028 |
| Opus 5 | $0.00005 | $0.00514 |
| Sonnet 5 | $0.00002 | $0.00206 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
image-node-qa 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Node QA
Workflow ID: $WORKFLOW_ID
Contract
Validate the image workflow artifacts. This is an artifact QA pass, not a render node. Do not call image generation, OpenAI APIs, CLI fallback scripts, or external services.
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- Render output if present:
$render.output
Write:
$ARTIFACTS_DIR/qa-report.md
Then output ONLY the QA JSON described below.
Checks
Selection checks:
template_idis one of the library template ids.categoryanddiscipline_cardare set and consistent with the mapping.example_case_idsis present and is an array of INTEGERS. The selection references library cases rather than pasting their prompt text.
Grounding checks (a citation must resolve, or must not be made):
- If the packet or prompt pack names
prompt_engine, then$ground.output.groundedistrueAND every citedexample_case_idsentry appears in$ground.output.resolved_case_ids. A cited id that is unresolved is a FAIL. - If
$ground.output.groundedisfalse, the pack carriesself_authored: trueand carries NOprompt_engineand NOexample_case_ids. Anything else is a FAIL. - No
*.local.jsonfile is quoted, copied, or listed in the manifest or the publishable pack.
Prompt pack checks:
- Required artifacts exist and contain parseable JSON where expected.
- Concept count matches expected count.
- Every concept carries BOTH a
baked_promptand anoverlay_prompt. - Overlay concepts include a
copyobject and a text-free scene with a forbid-text clause and reserved empty space. - Baked concepts quote
exact_textverbatim when it was requested. - Negative constraints include no watermark, no random logos, no garbled text, and no extra text beyond requested copy.
- No absolute local run paths, private system names, OpenAI API-key dependencies, or external render services appear in the public prompt pack.
- Public prompt-pack and packet JSON use relative artifact names. The QA report may include absolute local paths because it is a local run report.
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 · 113 lines · 11 tokens per session scan A fba1af0ae9c9
image-node-qa is a command published in the GitHub repository TheSmokeDev/taskchad-os (23 stars, last pushed 11d ago), licensed MIT. It adds 11 tokens to every session and 1,028 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
agent
Create and manage custom AI agents.
deep-review
Multi-pass deep code review — security, quality, and test gaps.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
tokenless-stats
Show Tokenless compression statistics.
arrecall
AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your flow.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.