Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add neuromechanist/research-skills/plugin install projectWrote 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/neuromechanist/research-skills/epic-dev)<a href="https://agentmods.dev/commands/neuromechanist/research-skills/epic-dev"><img src="https://agentmods.dev/badge/commands/neuromechanist/research-skills/epic-dev/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/neuromechanist/research-skills/epic-dev"><img src="https://agentmods.dev/badge/commands/neuromechanist/research-skills/epic-dev.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 | $0.00017 | $0.02891 |
| Opus 5.5 | $0.00007 | $0.01156 |
| Sonnet 5.5 | $0.00003 | $0.00578 |
| Haiku 4.5 | $0.00002 | $0.00289 |
Grade A, and why
epic-dev 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 8d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epic Development Workflow
Orchestrate multi-phase feature development using git worktrees, GitHub issues with sub-issues, and phased PR delivery. Load the project:workflow-reference skill immediately for reference context.
Core Principles
- Full automation: Execute all git, gh, and worktree commands automatically
- Confirm only at strategic points: epic plan, implementation plan, an accepted Critical finding that cannot be fixed within the phase, final merge
- Never stall: when blocked, follow
project:engineering-loopreferences/unblock-rules.md; every wait has a limit and a next action - Use absolute paths: Bash calls do not persist
cd; always use full worktree paths - Track progress: Use TodoWrite to track all phases and steps
- No emojis: Never use emojis in commits, PRs, or issues
- Model routing (per
project:agent-fanout): a Sonnet (xhigh) driver orchestrates; named Sonnet (xhigh) agents implement, review, and validate; epic design, unresolved architecture, and high-risk invariants go to Opus (xhigh), or Fable when available. - GitHub prose: Semantic line breaks remain the prose-source default, but text posted to GitHub (issue and PR bodies, comments, reviews, and discussions) is the exception. Keep each paragraph and list item on one source line, separate paragraphs with blank lines, and do not insert sentence- or clause-level newlines within a paragraph.
- Agent cleanup: After incorporating a final report, close/remove the one-off agent unless a concrete follow-up task is already assigned.
Phase 0: Repository Detection
Goal: Detect repo configuration and validate prerequisites.
Actions:
- Run
${CLAUDE_PLUGIN_ROOT}/bin/project-preflight --format jsonand parse the output. Keep the legacyproject-detect-repo-configfallback for installations that predate the preflight binary. - Validate all required values are present:
integration_branch,repo_root, andcurrent_branchmust be non-empty. If any are missing or ifERRORis set, report the error to the user and stop. - Validate gh only when a GitHub operation is about to run: require
has_gh=true, then usegh_command_status,gh_network_status,gh_auth_status, andgh_token_statusto give the repair-specific error. Do not report a generic unauthenticated state when the network or child-shell credential probe failed. - If
gh-sub-issueis needed and missing, install it:gh extension install agbiotech/gh-sub-issue - Store detected values:
integration_branch,repo_root,current_branch,native_agent_status, andnative_agent_surface. - Create initial todo list tracking all workflow phases
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.
- 8d ago Changed · +1 lines 9a450f7028ad
- 10d ago Changed · +3 lines 4c854da6745c
- 1mo ago Changed · +10 lines 5d535bfadc97
- 1mo ago Changed · +17 tokens per session 8a37982623f8
- 1mo ago First seen · 238 lines · 0 tokens per session scan A f558b41dbe7b
epic-dev is a command published in the GitHub repository neuromechanist/research-skills (49 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 17 tokens to every session and 2,891 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
taskstoissues
Deprecated: Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
arrange-workspace-flow-choose-workspace-layout
Phase 1 Choose Workspace Layout of arrange-workspace-flow.
github-notifications
Triage GitHub notifications: fetch, classify, report actions needed.
CLAUDE
The "commands" domain — multi-step coding commands, their versions, and their deployment.
step6-ship
Pipeline Step 6 — Ship the completed phase: commit, update roadmap, capture postmortem, optionally push and create PR.
release
You are a meticulous release manager. You coordinate releases, maintain changelogs, manage versioning, and ensure every release ships with proper documentation and rollback plans. You have zero tolerance for "just push it to prod" releases.