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 Firstp1ck/pi-coding-agent-forge --skill sailfishosgit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/sailfishos)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/sailfishos"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/sailfishos/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/firstp1ck/pi-coding-agent-forge/sailfishos"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/sailfishos.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 | $0.00015 | $0.01878 |
| Opus 5.5 | $0.00006 | $0.00751 |
| Sonnet 5.5 | $0.00003 | $0.00376 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
sailfishos 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sailfish OS operations
Treat Sailfish as mobile Linux, not generic Ubuntu, Arch, Fedora, Android, or an SDK VM. Establish actual capabilities before using examples. This skill is guidance, not an enforcement layer or permission to change a phone.
When to use
Use for Sailfish/SFOS diagnostics, BusyBox shell incompatibilities, PackageKit/RPM/SSU, devel-su, Chum/OpenRepos, systemd user services, Sailjail permissions, Qt/QML apps, Android AppSupport, SSH, storage, or SDK builds. Do not use it to administer an unrelated desktop distribution or Android device.
Inputs and assumptions
Establish the target device and OS release, normal user, architecture, execution backend (device, SDK target/emulator, or desktop host), requested operation, authorization boundary, and recovery path for disruptive changes. Do not assume a username, UID, IP, shell implementation, repository, helper shortcut, or installed package from a previous device. Personal observations belong in the harness's private memory, not this package.
Portable workflow
1. Identify context and capabilities
Read /etc/os-release; check id, uname -m, shell executable links, PATH, and relevant tools without dumping the environment. Read capability checks. Use normal-user read-only probes first.
On a confirmed Sailfish device, run the bundled inventory with its resolved absolute skill path:
/bin/sh <skill-directory>/scripts/inspect.sh
It reports OS, command availability, redacted repository URLs, storage, and selected service states. It refuses a non-Sailfish OS. A host-side run does not inspect a remote phone: transfer a reviewed helper or execute scoped probes on the authorized device. Use narrow file paths and bounded command timeouts.
2. Respect shell and privilege boundaries
Read shell and paths. A file named /bin/bash may be BusyBox rather than GNU Bash. Default to POSIX #!/bin/sh, quote paths, and verify flags; do not assume arrays, brace expansion, [[ ]], shopt, or GNU utility options. Keep dependent operations together and inspect the harness's shell-state semantics. Aliases and a previous root shell are not reliable authorization or execution state.
What ships with it
8 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.
- references/apps-and-development.md 7.5 KB
- references/capability-checks.md 1.4 KB
- references/packages-and-repositories.md 8.7 KB
- references/services-and-diagnostics.md 6.5 KB
- references/shell-and-paths.md 4.7 KB
- references/sources.md 7.8 KB
- scripts/inspect.sh 3.9 KB runs code
- scripts/package-available.sh 1.3 KB runs code
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.
- yesterday First seen · 96 lines · 15 tokens per session scan A 7cb4995004ec
sailfishos is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,878 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 2026-10-16.
Other skills, from other repositories
xcodebuildmcp
Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support). Use when the user mentions Xcode, xcodebuild, iOS builds/tests, or XcodeBuildMCP.
write-swift
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
animate-expo
Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and…
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
npm-docs
Use this skill whenever the user asks about npm, package management, publishing packages, semantic versioning, npm CLI commands, or Node.js dependencies. Covers npm 12.x including the registry, scopes, organizations, security (audit, provenance, 2FA), CI/CD integration, workspaces, scripts, .npmrc configuration, and…
using-xtool
This skill should be used when building iOS apps with xtool (Xcode-free iOS development), creating xtool projects, adding app extensions, or configuring xtool.yml. Triggers on "xtool", "SwiftPM iOS", "iOS on Linux", "iOS on Windows", "Xcode-free", "app extension", "widget extension", "share extension". Covers project…