Borrowing it
Nothing to install: this file belongs to Gainium/gainium-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Gainium/gainium-mcp/main/.claude/skills/gainium-dev-flow/SKILL.mdgit clone --depth 1 https://github.com/Gainium/gainium-mcpWrote 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/gainium/gainium-mcp/gainium-dev-flow)<a href="https://agentmods.dev/skills/gainium/gainium-mcp/gainium-dev-flow"><img src="https://agentmods.dev/badge/skills/gainium/gainium-mcp/gainium-dev-flow/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/gainium/gainium-mcp/gainium-dev-flow"><img src="https://agentmods.dev/badge/skills/gainium/gainium-mcp/gainium-dev-flow.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 | $0.04147 |
| Opus 5 | $0.00000 | $0.02073 |
| Sonnet 5 | $0.00000 | $0.00829 |
| Haiku 4.5 | $0.00000 | $0.00415 |
Grade A, and why
gainium-dev-flow 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 5d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gainium dev flow
This skill is distributed into every gainium repo — you're reading the
copy that lives in this repo. It intentionally contains no file
paths or examples specific to another repo (no app/app-sh
references): someone working in exchange-connector won't have app
checked out, and different repos use different frameworks (main-app's
hand-rolled COP singletons vs. NestJS providers elsewhere) and different
test tooling (mocha, Jest, hand-rolled expect() scripts all exist
across gainium repos — don't assume any one of them). Wherever this
file needs a concrete example, it tells you to go find this repo's
own, not to copy one from memory of another repo.
Two things changed here versus a generic spec-driven/hexagonal skill:
- Bug fixes go through the same seven gates as features, not a
shortcut. The only fork is what the spec (gate 1) contains — a bug
doesn't have new behaviour to define, it has existing behaviour to
diagnose. See Part 1's two spec templates. The harness's plan-mode UI
only gates approval of what you write — it does not gather
evidence, trace logs, or reproduce a bug for you. That's the agent's
job, done during gates 1–2, and it still gets written into a real
persisted
specs/NNN.slug.md, exactly like a feature. - This repo is probably not hexagonal today. Business rules are
probably mixed with DB/queue/exchange/HTTP calls in the same
function or class, wherever that pattern already exists here (check
this repo's own
CLAUDE.mdfor its documented architecture). New code should still be designed with SOLID + narrow ports (Part 3). Existing code gets modernized just-in-time, only where you're already touching it — never a drive-by rewrite. That extraction method is detailed in JIT-LEGACY-EXTRACTION-RUNBOOK.md; read it before doing any legacy touch-up, don't re-derive it here.
Repo layout note: Every artefact this skill produces (specs/,
plans/) lives inside this repo, not some shared location — never
at the gainium root. If this repo has a core/ git submodule (check
.gitmodules — a common gainium pattern: app↔app-sh,
exchange-connector↔exchange-connector-sh, websocket-connector↔
websocket-connector-sh, and others), treat files under core/ as
shared/public/deployed-platform-wide even though you're sitting in the
private counterpart repo — see Part 1's Blast Radius guidance and the
runbook's special case for this.
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.
- 5d ago First seen · 334 lines · 0 tokens per session scan A e464531534ab
gainium-dev-flow is a skill published in the GitHub repository Gainium/gainium-mcp (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,147 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 2026-09-04.
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.
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.