Borrowing it
Nothing to install: this file belongs to gotgenes/pi-anthropic-auth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gotgenes/pi-anthropic-auth/main/.pi/skills/fallow/SKILL.mdgit clone --depth 1 https://github.com/gotgenes/pi-anthropic-authWrote 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/gotgenes/pi-anthropic-auth/fallow)<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/fallow"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/fallow/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/gotgenes/pi-anthropic-auth/fallow"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/fallow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01802 |
| Opus 5.5 | $0.00013 | $0.00721 |
| Sonnet 5.5 | $0.00006 | $0.00360 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
fallow 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fallow
Fallow is a static analysis tool for TypeScript/JavaScript installed as a devDependency (2.104.0 at the time of writing; pnpm exec fallow --version).
It finds unused code, duplication, complexity hotspots, and refactoring targets, and it answers targeted questions about one file or one symbol.
Run it via pnpm fallow scripts or pnpm fallow <subcommand>, never npx.
Quick reference
pnpm fallow # full analysis: dead code + dupes + health
pnpm fallow:audit # changed-file audit (PR gate)
pnpm fallow:health # complexity, hotspots, refactoring targets
pnpm fallow:dead-code # unused files, exports, types, deps
pnpm fallow:dupes # duplicated code blocks
Question-shaped subcommands, each scoped smaller than a full run:
| Question | Command |
|---|---|
| What are this file's exports, imports, importers? | fallow inspect --file <path> |
| Who consumes this symbol? | fallow dead-code --trace <file>:<symbol> |
| What structural decisions does this change embed? | fallow decision-surface --base <ref> --format json |
| Where should a reviewer look in this change? | fallow review --brief --base <ref> |
| What is untested but reachable? | fallow health --coverage-gaps |
| What does this finding mean? | fallow explain <issue-type> |
The pi-packages copy of this skill documents fallow 3.x; guard, suppressions, similar-code, --type-aware, and --symbol-impact do not exist on 2.104.0.
Check pnpm exec fallow <subcommand> --help before adopting a command from there.
JSON output for programmatic use
Always invoke via pnpm --silent fallow … --format json --quiet 2>/dev/null and append || true.
The --silent is load-bearing: fallow exits 1 when issues are found (normal), and without --silent pnpm appends [ELIFECYCLE] Command failed with exit code 1. to stdout after the JSON — json.load then fails with "Extra data", and 2>/dev/null does not strip it.
Only exit code 2 is a real error.
Some subcommands print nothing in human format under --quiet (decision-surface and review --brief both, measured on 2.104.0) — read decision-surface as JSON, and run review --brief without --quiet.
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.
- 1mo ago Changed · +42 lines · -6 tokens per session 7cdad022341a
- 2mo ago First seen · 93 lines · 38 tokens per session scan A 0dd4a60a147e
fallow is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (426 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 1,802 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 skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
configuration-logging
Configure AuthCrunch diagnostic skip rules, Caddy credential redaction, and logger boundaries. Use for component/message filtering and safe credential diagnostics; authorization outcomes remain unchanged.
break-fix-troubleshooting
Diagnose caddy-security deployment and runtime failures from configs, logs, versions, and HTTP evidence. Use for focused fixes, unresolved support handoffs, or preparing break-fix issue reports.
provider-setup
Reports which delegation CLIs are installed and authenticated, installs missing ones, and stores the result. Use before delegating or when a provider errors.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.