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 SaikaAco/saika-hermes-skills --skill plangit clone --depth 1 https://github.com/SaikaAco/saika-hermes-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/saikaaco/saika-hermes-skills/plan)<a href="https://agentmods.dev/skills/saikaaco/saika-hermes-skills/plan"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/plan/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/saikaaco/saika-hermes-skills/plan"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/plan.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 | $0.00044 | $0.02634 |
| Opus 5 | $0.00022 | $0.01317 |
| Sonnet 5 | $0.00009 | $0.00527 |
| Haiku 4.5 | $0.00004 | $0.00263 |
Grade A, and why
plan 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 12d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Plan Mode
Lineage
This is an MIT-licensed adaptation of Jesse Vincent's Superpowers
writing-plans, reviewed at upstream commit 3dcbd5c4b48e02263fbf4a3c01e3fe4f81d584d9.
It retains comprehensive implementation planning, exact file paths, task decomposition, test-first examples, DRY/YAGNI discipline, explicit commands and expected results, interface contracts, placeholder checks, self-review, and execution handoff.
The Hermes adaptation adds strict plan-only authority, backend-relative .hermes/plans/ storage, project mutation boundaries, context-aware inference, task right-sizing without minute quotas, conditional execution routes, and explicit separation between planning and implementation authorization.
This adaptation is independently maintained and is not endorsed by Jesse Vincent or the Superpowers project. The complete upstream MIT notice is preserved in references/third-party-notices.md.
Core behavior
Use this skill when the user wants a plan rather than implementation.
For this invocation:
- inspect the project and requirements read-only as needed;
- do not implement code;
- do not edit project files except the approved plan markdown file;
- do not run mutating project commands, commit, push, deploy, or contact external systems;
- save one actionable markdown plan under the active project;
- report the saved path and stop unless execution is separately authorized.
A plan is an execution contract, not execution authority. Creating it does not authorize the changes it describes.
When to use
Use when:
- the user explicitly asks for a plan or invokes plan mode;
- settled requirements need implementation decomposition;
- a multi-step change needs exact files, interfaces, tests, and sequencing;
- work will be delegated and each implementer needs a self-contained task;
- implementation risk justifies design and verification review before mutation.
What ships with it
1 file 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.
- 12d ago First seen · 297 lines · 44 tokens per session scan A e570d5290e10
plan is a skill published in the GitHub repository SaikaAco/saika-hermes-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 44 tokens to every session and 2,634 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
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024)…
m365-entra-attack
Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. AADSTS code reference, user enumeration vectors (with hardening status), Smart Lockout math, Conditional Access bypass options, ROPC + SAML SSO browser flow, Burp/Playwright templates. Built from authorized red-team work where ROPC spray surfaced…
password-spray-methodology
End-to-end password spray playbook. User enumeration, lockout detection, password pattern generation, spray execution across all protocols, error code differentials, and engagement discipline. Unifies M365/Entra, Okta, Exchange, Kerberos, SharePoint, XMLRPC, OIDC, and AD SMB/WinRM spraying into one methodology.
cache-attack
Poison CDN cache or deceive when X-Cache header is detected.
hunt-django
Hunt Django-specific vulnerabilities: DRF permission gaps, ORM injection, and admin exploitation.
tianya-gods-team
A decision-making system in which 20 fictional specialist viewpoints analyze one question in parallel before a coordinating AI combines them. It covers areas such as history, economics, relationships, technology, mysteries, and culture.