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/sneg55/agent-starter/new-projectnpx skills add sneg55/agent-starter --skill new-projectgit clone --depth 1 https://github.com/sneg55/agent-starterWrote 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/sneg55/agent-starter/new-project)<a href="https://agentmods.dev/skills/sneg55/agent-starter/new-project"><img src="https://agentmods.dev/badge/skills/sneg55/agent-starter/new-project.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.03628 |
| Opus 5 | $0.00020 | $0.01814 |
| Sonnet 5 | $0.00008 | $0.00726 |
| Haiku 4.5 | $0.00004 | $0.00363 |
Grade D, and why
new-project scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Add setup instructions here --> Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
HOOKS_VER=$( [ -f ~/.claude/hooks/.agent-starter-version ] && cat ~/.claude/hooks/.agent-starter-version || echo "" ) How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project Bootstrap
Use when starting a new project from scratch. Scaffolds a complete AI-friendly project following the agent-starter patterns: feature-based directory structure, CLAUDE.md with memory taxonomy, config files, optional hooks and skills, first commit.
For existing projects, use /adopt-project instead.
Phase 0: Detect what's already installed
Hooks and skills install system-wide under ~/.claude/, so they're shared
across every project. Detect them first and never ask about components that are
already present. Run:
# Hooks: install.sh stamps this file with the installed version
HOOKS_VER=$( [ -f ~/.claude/hooks/.agent-starter-version ] && cat ~/.claude/hooks/.agent-starter-version || echo "" )
HOOKS_N=$( ls ~/.claude/hooks/*.sh 2>/dev/null | wc -l | tr -d ' ' )
# Skills: the starter skills this bootstrap installs
for s in commit commit-push-pr simplify remember dream new-project adopt-project reflect; do
[ -d ~/.claude/skills/$s ] && echo "skill:$s present" || echo "skill:$s missing"
done
echo "hooks: version ${HOOKS_VER:-none}, $HOOKS_N scripts"
Interpret the output:
- Hooks installed if
.agent-starter-versionexists (or hook scripts are found). Record the stamped version. - Skills installed per directory listed as
present.
Carry this into the interview and scaffold: only ask about, and only install,
what's missing. If a stamped hooks version is present but older than the
repo VERSION (checked in Phase 1 once you have the repo path), note that an
update is available and offer to re-run install.sh (idempotent) - don't force it.
Phase 1: Interview
Ask these questions one at a time before taking any action:
- Project name - what is the name of the project?
- Description - one sentence describing what it does.
- Tech stack - language, framework, package manager (e.g. "TypeScript, Next.js, pnpm").
- Optional components - ask only about what Phase 0 reported as missing.
If hooks and all skills are already installed, skip this question entirely -
state what was detected ("Hooks v0.4.4 and all 8 skills already installed
system-wide, skipping") and move on. Otherwise offer the missing set:
- Hooks (auto-enforce file size limits, lint-on-save, silent-error and dangerous-command blocking, codebase health checks at
~/.claude/hooks/) - Skills (commit, commit-push-pr, simplify, remember, dream, new-project, adopt-project, reflect at
~/.claude/skills/) - Both
- Neither
- Hooks (auto-enforce file size limits, lint-on-save, silent-error and dangerous-command blocking, codebase health checks at
- Repo path - what is the local path to the agent-starter repo? (e.g.
~/code/agent-starter). Always required: the CLAUDE.md template, foundation templates, and lint configs are all copied from the repo. (Hooks and skills also install from here when selected and not already present.)
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 · +5 lines 350bbb4c7f4b
- 6d ago First seen · 321 lines · 41 tokens per session scan D 27de174b4db3
new-project is a skill published in the GitHub repository sneg55/agent-starter (76 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 3,628 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
economist-style
Apply The Economist style guide to written content. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity. Detects weasel words, fillers, passive voice, and style issues.
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
ignore-setup
Set up a project so Claude stops discovering lockfiles, generated code, minified assets and binaries on every search — a managed .ignore, the Glob setting that makes Glob obey it, and a short read-deny list for secrets. Use when someone asks for a .claudeignore, asks to exclude files from the context, says Claude…
cutting-planes-valid-inequalities
When the user wants to strengthen a MIP with cutting planes and valid inequalities — deriving cover, clique, MIR, or Gomory cuts, writing separation routines, and adding them as user cuts or lazy constraints via Gurobi callbacks. Also use when the user mentions "valid inequalities," "cutting planes," "separation…