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 arozumenko/sdlc-skills --skill automation-scopinggit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/automation-scoping)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/automation-scoping"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/automation-scoping/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/arozumenko/sdlc-skills/automation-scoping"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/automation-scoping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 579 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00122 | $0.09599 |
| Opus 5 | $0.00061 | $0.04799 |
| Sonnet 5 | $0.00024 | $0.01920 |
| Haiku 4.5 | $0.00012 | $0.00960 |
Grade A, and why
automation-scoping 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 12d 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 — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Scoping
Estimate how much active-agent time (and, derived from that, how much money) it will cost to automate a scope of test cases — before the batch pipeline runs, sometimes before the target app is even reachable. This is the tool that turns "we think this will take a while" into a number with a stated confidence level, defensible enough to put in a proposal.
Core philosophy — a cone of uncertainty, not a fortune-telling machine. Confidence narrows as more is known, and every mode below states honestly where it sits on that cone:
Mode 1 (blind, case text only) → Mode 2 (scored sample, extrapolated) → Mode 3 (app-informed) → delivery → Mode 4 (calibrate against what actually happened)
widest band narrower band the model gets sharper for next time
The one number this skill will never produce is a bare point estimate.
Every output is a range with a named confidence tier
(references/scoping-report-format.md § Confidence statement). A presales
number without its band is the anti-pattern this whole skill exists to
replace.
Two currencies, reported side by side, never reconciled into one. Agent
cost (active-minutes → $, the base × tier × novelty model) answers what
will this burn. Work size (XS/S/M/L/XL → Service Points, 1 SP = 1 hour of
conventional engineer effort) answers how big is this and what would it
cost the old way. They diverge on purpose, and the gap is the engagement's
value story. The sharp edge is foundation work — framework, CI, abstraction
layer, data layer — which on the source engagement was 25.8% of delivered
SP but only 5.9% of token cost: price it in agent-dollars and a quarter of
the engagement vanishes into rounding. Full reasoning and the measured
numbers: references/sizing-rubric.md.
What this is built on, so it isn't guessed from scratch
What this factory/family already does, stitched together rather than reinvented:
What ships with it
16 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.
- references/calibration-log.md 45 KB
- references/calibration-methodology.md 8.3 KB
- references/complexity-taxonomy.json 30 KB
- references/complexity-taxonomy.md 19 KB
- references/foundation-catalog.json 16 KB
- references/sampling-methodology.md 3.1 KB
- references/scoping-report-format.md 9.8 KB
- references/sizing-rubric.md 14 KB
- scripts/build-training-set.mjs 11 KB runs code
- scripts/build-training-set.test.mjs 7.6 KB runs code
- scripts/calibrate.mjs 7.6 KB runs code
- scripts/calibrate.test.mjs 1.2 KB runs code
- scripts/score-cases.mjs 44 KB runs code
- scripts/score-cases.test.mjs 26 KB runs code
- scripts/sizing.workflow.mjs 9.9 KB runs code
- scripts/sizing.workflow.test.mjs 3.6 KB runs code
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.
- 12d ago First seen · 657 lines · 122 tokens per session scan A b866ffdeea37
automation-scoping is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 9,599 once invoked, about $0.0006 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 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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.