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.
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/commands/joaquimscosta/arkhe-claude-plugins/develop)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/develop"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/develop/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/commands/joaquimscosta/arkhe-claude-plugins/develop"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/develop.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 | $0.00016 | $0.00387 |
| Opus 5.5 | $0.00006 | $0.00155 |
| Sonnet 5.5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
develop 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.
What it actually says
Develop
Guided feature development through a 6-phase SDLC pipeline with plan persistence.
Quick Start
/develop add user authentication # Full pipeline
/develop add logout button --auto # Autonomous mode
/develop create plan for X --plan-only # Plan only
/develop @arkhe/specs/01-auth/ # Resume existing
/develop @arkhe/specs/01-auth/ --verify-arch # Verify architecture alignment
/develop @arkhe/specs/01-auth/ --verify-impl # Verify implementation completeness
/develop @arkhe/specs/01-auth/ --verify-arch --verify-impl # Full audit
Flags
| Flag | Effect |
|---|---|
--plan-only |
Stop after Phase 2 (save plan, don't implement) |
--validate |
Enable opus-level validation in Phase 4 |
--phase=N |
Execute specific phase only |
--auto |
Autonomous mode (no checkpoints) |
@path |
Resume from existing plan |
--verify-arch |
Verify implementation matches plan.md architecture |
--verify-impl |
Verify implementation meets spec.md requirements |
Implementation
Invoke the Skill tool with skill name "core:sdlc-develop" and arguments: $ARGUMENTS
The skill handles all six phases: Discovery → Requirements → Architecture → Workstreams → Implementation → Summary.
For detailed phase documentation, see core/skills/sdlc-develop/SKILL.md.
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 · 41 lines · 16 tokens per session scan A 693775c75cef
develop is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 387 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
permissions
Create or update DOGMA-PERMISSIONS.md to configure what Claude can do autonomously.
merge
You are executing the /hydra:merge command. Merge a worktree branch back into the current branch.
forge-compact-task
Compact context with dotforge-standardized hint that preserves decisions, files modified, pending TODOs, behaviors disabled, and last commit. Use at 80% context window instead of waiting for auto-compact.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
forge-audit
Audit project's Claude Code config and calculate score (0-10).