Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ivanhoinacki/team-exp-claude-confignpx agentmods add skills/ivanhoinacki/team-exp-claude-config/feature-devWrote 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/ivanhoinacki/team-exp-claude-config/feature-dev)<a href="https://agentmods.dev/skills/ivanhoinacki/team-exp-claude-config/feature-dev"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/feature-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/skills/ivanhoinacki/team-exp-claude-config/feature-dev"><img src="https://agentmods.dev/badge/skills/ivanhoinacki/team-exp-claude-config/feature-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 | $0.00092 | $0.06496 |
| Opus 5.5 | $0.00037 | $0.02598 |
| Sonnet 5.5 | $0.00018 | $0.01299 |
| Haiku 4.5 | $0.00009 | $0.00650 |
Grade A, and why
feature-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 2mo 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 — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 0: Vault RAG (MANDATORY, BEFORE any Read/Grep)
You MUST call query_vault(query, service_filter) BEFORE reading codebase files or external sources for any LE-related task. This is enforced by hook. No exceptions.
Feature Development, Discovery, Plan & Implementation
Working Directories
Always use these directories as primary sources for discovery, patterns, and implementation:
- Obsidian workspace (docs, plans, features):
__VAULT_ROOT__ - Codebase (all LE services):
__CODEBASE_ROOT__
Common Agent Mistakes
These mistakes have been observed across feature development sessions and led to rework, rejected PRs, or production issues.
- Skipping discovery: Jumping straight to coding without completing Phases 1-3. Why: discovery prevents rework. Past features that skipped it had 2-3 rework cycles when reviewers found existing utils or conflicting business rules.
- Creating new utils when one exists: Writing a new helper function without checking if the repo already has one. Why: a previous code review flagged this. Duplicate utils diverge over time and create maintenance burden.
- Ignoring existing patterns: Writing code that doesn't match the patterns in adjacent files. Read 2-3 files in the same directory before writing new code. Why: inconsistent patterns confuse future maintainers and trigger review comments.
- Not consulting pitfalls.md: The vault's pitfalls.md contains 66+ one-liner gotchas that prevent known bugs. Why: these pitfalls were each discovered the hard way. Checking takes 30 seconds, fixing the bug takes hours.
- Over-engineering: Adding abstractions, configurability, or "future-proofing" that wasn't requested. Why: the user explicitly wants minimal, focused changes. Over-engineering was flagged in multiple past PR reviews as scope creep.
- Missing test updates: Implementing a feature without updating or creating tests for the changed modules. Why: untested code is the #1 source of regressions and will be caught by
/code-reviewanyway. - Breaking the dependency chain: Not verifying that skill chain (feature-dev -> deslop -> code-review -> commit -> create-pr) is followed. Why: each step feeds the next. Skipping deslop means code-review finds AI slop instead of real issues.
- Wrong admin portal (www-ee-admin vs www-le-admin): Building a feature in the wrong admin project. www-le-admin = LE main admin (internal ops, content curation, attractions, experience management). www-ee-admin = White Label vendor/partner features. Why: EXP-3538 was built entirely in www-ee-admin, had to be redone. During discovery, always verify which portal matches the feature type.
- www-le-admin worktree missing public/ directory: After creating a worktree for www-le-admin, the
public/directory is missing (gitignored). Express BFF fails to serve pages. Fix:cp -r ../www-le-admin/public/ ./public/after worktree creation. Why: EXP-3538 lost time debugging empty responses. - Attempting to fix errors without checking KB first: When a build/test/runtime error occurs during implementation, immediately trying to fix it without running
query_vault+grep pitfalls*.md. Why: the KB has documented fixes for dozens of errors. A 2-second vault check prevents 10-minute retry loops. MANDATORY: on ANY error, check vault BEFORE attempting fix (see08-behavioral-standards.mdrule 3).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 523 lines · 92 tokens per session scan A 425814ef169b
feature-dev is a skill published in the GitHub repository ivanhoinacki/team-exp-claude-config (2 stars, last pushed 26d ago), licensed MIT. It adds 92 tokens to every session and 6,496 once invoked, about $0.0004 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
me-card
Render the user's saved /.me/ context as a single ASCII-art infographic card. Use when the user asks to "show my info", "print my card", "render my profile", "me card", "ascii infographic of my dot-me", or invokes the /me-card shortcut. Read-only — never writes to /.me/.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).