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 shrekshrek/project-workflow/plugin install project-workflowWrote 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/shrekshrek/project-workflow/feature-init)<a href="https://agentmods.dev/skills/shrekshrek/project-workflow/feature-init"><img src="https://agentmods.dev/badge/skills/shrekshrek/project-workflow/feature-init/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/shrekshrek/project-workflow/feature-init"><img src="https://agentmods.dev/badge/skills/shrekshrek/project-workflow/feature-init.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 | $0.00043 | $0.00391 |
| Opus 5.5 | $0.00017 | $0.00156 |
| Sonnet 5.5 | $0.00009 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
feature-init 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.
What it actually says
Feature Init
Match the user's language. Read ${CLAUDE_PLUGIN_ROOT}/docs/actions/feature-init.md completely before acting; it owns discovery, records, authorization, and safety rules.
Claude execution details:
- Interpret
$ARGUMENTSin the ongoing conversation. Resolve the target root explicitly; all writes stay below it. Choose a kebab-case slug only when an authorized new record is needed. - Read root/applicable nested
AGENTS.mdand active current truth. Claude-local.claude/rules/are host-specific convention inputs when applicable. - Only when creating a new feature record, invoke
${CLAUDE_PLUGIN_ROOT}/scripts/materialize-feature-artifact.cjs; requireCLAUDE_PLUGIN_ROOTand never search another runtime cache or bypass its no-clobber gate. Skip materialization when reusing a record or when no record is needed. - Under the shared execution contract, dispatch a fresh
decision-completeness-auditoronly at the canonical material-choice/conflicting-or-weak-evidence boundary; ordinary work with directly traceable values isN/A. Use main-session fallback only when canonical dispatch is unavailable or fails, and record the observed reason. Report canonical Reviewer execution evidence whenever this audit boundary applies. - Create no production implementation code and never commit. A separately authorized bounded trial follows the canonical discovery rules. Return control to the enclosing request as directed by the canonical action.
- If materialization reports an occupied directory, leave it untouched and rerun feature-init to recompute the number.
Report the useful conclusion, record disposition, evidence, and next action without adding an adapter-specific schema.
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 Changed 66afc1092985
- 1mo ago First seen · 25 lines · 43 tokens per session scan A 174139b85d46
feature-init is a skill published in the GitHub repository shrekshrek/project-workflow (2 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 391 once invoked, about $0.0002 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.