Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsnpx agentmods add skills/fledgeling-co/fledgeling-plugins/lotWrote 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/fledgeling-co/fledgeling-plugins/lot)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/lot"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/lot/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/fledgeling-co/fledgeling-plugins/lot"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/lot.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 | $0.00086 | $0.01517 |
| Opus 5.5 | $0.00034 | $0.00607 |
| Sonnet 5.5 | $0.00017 | $0.00303 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
lot 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lot — the queue, under a risk limit
Two bad options and one good one. Signing every item individually is what nobody finishes; promoting
the whole queue at once is not checking. The third way is a century old in manufacturing and in
clinical laboratories: accept the lot under a declared risk limit (I2).
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It turns positioning.md's six verdict-leak channels into a table where the script closes two and the run must close four, makes the two census classes carry counted denominators, and sends an exit 3 to assay rather than to --unmeasured-suite. Other models skip it.
Procedure
-
Measure the suite first, or say you did not. Every number below is a number about items whose evidence is the test suite, so the plan inherits that suite's fault sensitivity — and more than half of over 15,000 generated mutants survived a passing unit, integration and system suite (
C18).lot_plan.pyexits 3 without.warrant/suite-health.json, namingwarrant:assayas the step that produces it.--unmeasured-suiteplans anyway and records the omission in the plan and on every run, the same way--raterecords an override, so a plan built over an unmeasured suite cannot pass as one built over a measured one. -
Size the sample.
python3 scripts/lot_plan.py --root <repo> --lot <n> --lot-id <id>The tolerable error rate comes from the warrant rather than from the invocation, so a run cannot quietly loosen it. The plan emits the initial sample size, the sequential stopping rule and the escalation path, and shows the arithmetic in the human output so the number can be argued with.
-
Build the queue blind.
python3 scripts/blind_queue.py --root <repo> --items <items.json> --lot-id <id> \ --seeds <seeds.local.json>The reviewer artifact is built from an allowlist rather than by stripping fields, so a verdict cannot reach it by construction. Forcing one through is possible only with
--carry verdict, and that is refused: exit 2, naming every way the field would have leaked, by field name and by value. It writes a second file, an operator key at mode 600, holding the seed positions the reviewer must not see.
What ships with it
1 file 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.
- 1mo ago Changed ddea9a3749e0
- 1mo ago First seen · 117 lines · 86 tokens per session scan A ffd9e6e99ea5
lot is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 1,517 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.