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 postindustria-tech/agentic-toolkit --skill step-developmentgit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/step-development)<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/step-development"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/step-development/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/postindustria-tech/agentic-toolkit/step-development"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/step-development.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 | $0.00072 | $0.01811 |
| Opus 5.5 | $0.00029 | $0.00724 |
| Sonnet 5.5 | $0.00014 | $0.00362 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
step-development 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD Step Development
Develop BDD step definitions for a feature by parsing Gherkin, diffing against existing steps, and walking a structured implementation workflow. Each step goes through research, review, implement, and verify phases.
When to Use
/qa-bdd-step-development tests/bdd/features/my-feature.feature-- wire ALL missing steps/qa-bdd-step-development tests/bdd/features/auth-*.feature-- fix broken steps (re-enumerates from Gherkin)
Does NOT Cover
- Writing
.featurefiles (write Gherkin first, then invoke this) - Non-BDD tests (unit tests, integration tests)
Protocol
Step 1: Enumerate Missing Steps
Parse Gherkin and diff against existing step definitions:
# 1. Find all step text in the feature file(s)
grep -E '^\s+(Given|When|Then|And|But) ' tests/bdd/features/<feature>.feature \
| sed 's/^\s*//' | sort -u > /tmp/gherkin_steps.txt
# 2. Find all registered step patterns
grep -rn '@given\|@when\|@then' tests/bdd/steps/ \
| grep -oP "(?:parse|re)\(['\"])(.*?)(['\"])" | sort -u > /tmp/existing_patterns.txt
# 3. Diff -- unmatched lines are missing steps
# (Manual matching needed -- patterns use parsers.parse/re)
Alternatively, use ast-grep for structural queries:
# Find all existing Given steps
ast-grep --pattern '@given($_)' tests/bdd/steps/
# Find all existing When steps
ast-grep --pattern '@when($_)' tests/bdd/steps/
# Find all existing Then steps
ast-grep --pattern '@then($_)' tests/bdd/steps/
# Steps using parsers.parse()
ast-grep --pattern '@given(parsers.parse($_))' tests/bdd/steps/
Group missing steps into batches of 3-5 by scenario affinity (same scenario or related scenarios that share Given context).
Step 2: Research Each Batch
For each batch of missing steps:
- Identify test level (see decision table below)
- Find related production code that the steps will exercise
- Find existing step patterns to follow (look at neighboring step files)
- Identify factories available for test data setup
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 First seen · 219 lines · 72 tokens per session scan A 5a27b3a1ccbf
step-development is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 72 tokens to every session and 1,811 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 2026-08-31.
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.