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 skills add arpitbbhayani/ape-skills --skill ape-plan-projectgit clone --depth 1 https://github.com/arpitbbhayani/ape-skillsWrote 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/arpitbbhayani/ape-skills/ape-plan-project)<a href="https://agentmods.dev/skills/arpitbbhayani/ape-skills/ape-plan-project"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-plan-project/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/arpitbbhayani/ape-skills/ape-plan-project"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-plan-project.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 | $0.00056 | $0.03319 |
| Opus 5 | $0.00028 | $0.01659 |
| Sonnet 5 | $0.00011 | $0.00664 |
| Haiku 4.5 | $0.00006 | $0.00332 |
Grade A, and why
ape-plan-project 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 10d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phased Spec Decomposition
Take one product + engineering spec and turn it into an ordered sequence of phases, each with its own standalone design document. The output is meant to be handed to a coding agent one phase at a time -- every document must be implementable on its own, with no unresolved questions.
North star: every phase document should leave zero design decisions for the implementer. Not "an agent probably wouldn't need to ask a question" -- an agent literally cannot make a different reasonable choice than the one the document specifies, because every choice is already made and written down.
Input
Accept a PRD, an engineering design doc, a combined spec, or rough notes that mix product intent with technical detail. If the input only covers product intent, infer a reasonable engineering approach and mark it as an assumption. If it only covers engineering, infer the product framing (who benefits, what they can now do) for each phase.
Verify Before Writing
If a codebase is available, read it before writing any engineering content.
Cite what exists today with path:line, not from memory or from what the
spec assumes. A phase document that describes "current state" without having
read the current state is a guess, not a spec. If no codebase exists yet
(greenfield), say so explicitly and proceed on the spec alone.
For each phase, note what already exists that the phase can reuse -- an existing service, table, endpoint, or library that solves part of the problem. Never let a phase rebuild something the codebase already has.
Tech Stack Choices
Brownfield (existing codebase): the stack is not a decision to make -- it's whatever Verify Before Writing found. Match the existing language, framework, database, and libraries. Introducing a new one requires a stated reason (the existing stack genuinely cannot do what this phase needs), never preference or unfamiliarity with what's there.
Greenfield (no codebase yet): Phase 1's document must pin the full stack once -- language, framework, database, hosting/deploy target, and any non-trivial third-party library -- each with a one-line rationale. Every later phase inherits this silently as a given; never re-open or re-litigate the stack in a later phase's document.
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.
- 10d ago First seen · 287 lines · 56 tokens per session scan A e5567685080b
ape-plan-project is a skill published in the GitHub repository arpitbbhayani/ape-skills (38 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 3,319 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".