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 agentmods add skills/koroqe/claude-code-sdlc/develop-featurenpx skills add Koroqe/claude-code-sdlc --skill develop-featuregit clone --depth 1 https://github.com/Koroqe/claude-code-sdlcWhat 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 | $0.00033 | $0.07590 |
| Opus 5 | $0.00016 | $0.03795 |
| Sonnet 5 | $0.00007 | $0.01518 |
| Haiku 4.5 | $0.00003 | $0.00759 |
Grade A, and why
develop-feature 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 2d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: Develop Feature
Autonomously implement a complete feature from request to merge-ready. This command chains the full agency SDLC pipeline without stopping for human input.
Arguments
The feature to build is $feature (also available as $ARGUMENTS). When it is empty, ask the user what to build before starting Phase 1 — do NOT infer a feature from surrounding context.
Literal-token flag rule: a documented flag is active ONLY if its literal token appears in $ARGUMENTS. Never infer that a flag was passed because the documentation describes it.
Preflight: Memory Layer Check
Run this FIRST, before Phase 1. It takes one Read.
-
Check that
~/.claude/claude.mdexists and contains the marker heading## Autonomous Development Workflow (MANDATORY). -
If the file is missing, or the marker is absent, print this warning verbatim and continue anyway:
WARNING: the SDLC memory layer is not installed.
~/.claude/claude.mdis missing or does not contain the pipeline instruction, so the autonomous workflow is not active for unprefixed requests in this session. Installing the plugin alone is not sufficient — runbash install.shfrom the claude-code-sdlc repo to install the memory layer. -
Never block on this check. A missing memory layer degrades autonomy; it does not invalidate this run. Warn once and proceed to Phase 1.
Known limitation: this preflight only fires when this skill is invoked explicitly. An unprefixed natural-language feature request bypasses it entirely, because nothing runs. That gap closes when the SessionStart hook lands (roadmap F2a).
Pipeline
(The workflows named below — /bootstrap-feature, /implement-slice, /merge-ready — are plugin skills, resolvable in full as /claude-code-sdlc:<name>. The bare form used throughout this file works automatically as long as no other installed plugin defines a skill by the same name.)
Phase 0: Triage
Defined once, authoritatively and self-sufficiently, here — mirroring how the Preflight: Memory Layer Check above stands alone. Restated with identical signal text in src/claude.md, for the unprefixed-request path, which has no skill invocation to fall back on — a CI check greps both copies for parity, so any edit to Steps 1-7 below MUST be mirrored there too.
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.
- 2d ago First seen · 249 lines · 33 tokens per session scan A 82f5a911aa32
develop-feature is a skill published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 7,590 once invoked, about $0.0002 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
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
test-generation
Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.
code-assist
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.