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 skills add dmmdea/offload-harness --skill gimpgit clone --depth 1 https://github.com/dmmdea/offload-harnessWrote 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/dmmdea/offload-harness/gimp)<a href="https://agentmods.dev/skills/dmmdea/offload-harness/gimp"><img src="https://agentmods.dev/badge/skills/dmmdea/offload-harness/gimp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dmmdea/offload-harness/gimp"><img src="https://agentmods.dev/badge/skills/dmmdea/offload-harness/gimp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00719 |
| Opus 5.5 | $0.00000 | $0.00288 |
| Sonnet 5.5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
gimp 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 1mo 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.
What it actually says
GIMP 3.2 (autonomous driving)
This file only routes. Every fact, command line, procedure name and trap lives in
reference/ (not auto-loaded — open the file the task needs). Facts there are tagged
[measured]/[doc]/[community]/[inferred]; anything untagged is a bug in the doc.
Start here: reference/README.md — the index plus the ten rules (memorize those; they
cover 90 % of what goes wrong: no default batch interpreter, --quit is mandatory, the
plug-in process outlives gimp-console, alpha before resize, exact font names, verify by file).
| Task | Open |
|---|---|
| Which box has GIMP, paths, embedded Python, profile/log/temp dirs, verifier tools | reference/01-hosts-install.md |
| Console vs GUI vs batch vs MCP, one-GIMP-per-machine, MCP start / tool list / stop, teardown | reference/02-connection-modes.md |
Exact gimp-console-3.2.exe command lines, flags, exit codes, quoting, stdin batch |
reference/03-cli-batch.md |
Writing Python against gi.repository.Gimp (classes, methods, enums, PDB calls, GEGL filters) |
reference/04-api-reference.md |
| Designer words → operations (resize, crop, canvas, text, outline, shadow, remove BG, composite, thumbnail sizes) | reference/05-editing-playbook.md |
| Export formats that actually work here, per-format args, how to verify the file | reference/06-export-formats.md |
| Script-Fu 3, Python plug-in registration, the gimp-mcp plug-in as a model | reference/07-scripting-scriptfu-python-plugins.md |
| Something returned None/False/NULL, hung, or wrote the wrong file | reference/08-failure-modes.md |
| Exact PDB signatures on this build (902 procs), enums, GEGL op properties, fonts, export matrix | reference/live-dump-2026-09-01.json (grep it; do not load whole) |
Working rules that are not GIMP facts: console mode only unless a human wants to watch; kill the whole GIMP process tree when done (never leave a GIMP window or plug-in process); temp scripts go in the session scratchpad and are deleted; outputs are verified with a second tool (ffprobe / Pillow / pdfinfo), never by return code alone.
What ships with it
10 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.
- reference/01-hosts-install.md 10 KB
- reference/02-connection-modes.md 9.4 KB
- reference/03-cli-batch.md 7.1 KB
- reference/04-api-reference.md 23 KB
- reference/05-editing-playbook.md 12 KB
- reference/06-export-formats.md 7.8 KB
- reference/07-scripting-scriptfu-python-plugins.md 9.2 KB
- reference/08-failure-modes.md 13 KB
- reference/live-dump-2026-09-01.json 608 KB
- reference/README.md 7.3 KB
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.
- 1mo ago Changed 7580d02b85bc
- 1mo ago First seen · 32 lines · 0 tokens per session scan A 9231f4e7bf64
gimp is a skill published in the GitHub repository dmmdea/offload-harness (4 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 719 tokens. 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 2026-09-05.
Other skills, from other repositories
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.