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/shrekshrek/project-workflow/feature-initnpx skills add shrekshrek/project-workflow --skill feature-initgit clone --depth 1 https://github.com/shrekshrek/project-workflowWhat 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 | $0.00043 | $0.00370 |
| Opus 5 | $0.00022 | $0.00185 |
| Sonnet 5 | $0.00009 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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
$ARGUMENTSin the ongoing conversation. Resolve the target root explicitly; all writes stay below it. Choose a kebab-case slug only when an authorized new record is needed. - Read root/applicable nested
AGENTS.mdand active current truth. Claude-local.claude/rules/are host-specific convention inputs when applicable. CLAUDE_PLUGIN_ROOTis required; invoke${CLAUDE_PLUGIN_ROOT}/scripts/materialize-feature-artifact.cjsand never search another runtime cache or bypass its no-clobber gate.- 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 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 2d ago), licensed MIT. It adds 43 tokens to every session and 370 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 2026-08-31.
Other skills, from other repositories
implement
Test-driven implementation of a plan produced by /plan: loads the JSON tracker, then per chunk writes a failing test, implements until it passes, and runs a two-agent quality gate (review-impl conformance + red-team correctness). Use after /plan has produced an approved tracker. Requires a tracker whose planreview…
spec
Structured specification process: explores code, generates user stories with testable acceptance criteria, resolves ambiguities through interactive clarification, validates completeness, and outputs a lightweight spec. Use before /plan to clarify WHAT to build.
plan
Structured planning process: explores the code, decomposes a feature into independently-testable TDD chunks with a dependency graph, writes a JSON tracker, and gates the plan through an independent review-plan agent before any code is written. Use after /spec (or on its own) and before /implement, to decide HOW to…
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.