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 Solatrader/syft-news-skills --skill syft-guidance-rulebookgit clone --depth 1 https://github.com/Solatrader/syft-news-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/solatrader/syft-news-skills/syft-guidance-rulebook)<a href="https://agentmods.dev/skills/solatrader/syft-news-skills/syft-guidance-rulebook"><img src="https://agentmods.dev/badge/skills/solatrader/syft-news-skills/syft-guidance-rulebook/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/solatrader/syft-news-skills/syft-guidance-rulebook"><img src="https://agentmods.dev/badge/skills/solatrader/syft-news-skills/syft-guidance-rulebook.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 | $0.00058 | $0.00453 |
| Opus 5 | $0.00029 | $0.00227 |
| Sonnet 5 | $0.00012 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
syft-guidance-rulebook 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.
What it actually says
Syft Guidance Rulebook
Use this skill when the user expresses something that may deserve long-term storage.
Goal
Maintain a persistent user guidance document that future profile, briefing, and storyline work can read as parallel guidance.
Recommended file:
profiles/user_guidance_rulebook.md
If a workspace already uses a JSON rulebook, reuse it instead of forcing Markdown. The critical behavior is the workflow, not the file format.
Golden rule
Never store a long-lived rule directly from one raw user sentence.
Always do this first:
- summarize your understanding
- ask whether the summary is correct
- ask whether the user wants it persisted
- only then write it into the rulebook
Good candidates for storage
- long-term content preferences
- structural editorial preferences
- storyline / branch handling preferences
- search extension preferences
- recurring dislikes or red lines
Bad candidates for storage
- one-off requests for today only
- temporary formatting asks
- speculative guesses that the user has not confirmed
Rulebook entry shape
Each stored rule should preserve:
- id
- name
- scope
- kind
- priority
- status
- canonical guidance text
- short rationale
- source note
- confirmed date
Read references/rulebook-template.md before editing the file.
Scope guidance
Use:
allfor rules that should influence almost everythingeditorialfor daily briefing behaviorstorylinefor event-tree organizationsyft_searchfor search completion behaviorrecommendationfor future recommendation logic
Priority guidance
Use broad bands:
85-100: strong, identity-defining, should almost always affect output65-80: meaningful preference, usually keep active40-60: soft preference<40: weak or situational preference
What ships with it
2 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.
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 · 81 lines · 58 tokens per session scan A 22e7bf713924
syft-guidance-rulebook is a skill published in the GitHub repository Solatrader/syft-news-skills (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 453 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 2026-08-31.
Other skills, from other repositories
syft-cli-assistant
Use when the user needs help installing, authenticating, troubleshooting, or using the local syft CLI for Syft AI news workflows. Trigger for first-time setup, syft login or syft status, followed-topics inspection, top stories, personal search, global search, Codex skill installation via syft install-skill, or any…
youtube-content
YouTube Data API — search, video details, channel info, transcripts.
ccs
Search local Claude Code, Codex, and Cursor user-prompt history (read-only). Use when you need a past prompt, want to grep coding-agent session text, or pipe prompt history as JSON.
git-memory-recall
You are retrieving facts from Tau Git Memory.
git-memory-remember
Save one durable memory into Tau Git Memory.
the-news
This skill gives agents access to the main headlines of many newspapers and news sites, across 20 countries, via a public API. The API has two modes: a live mode, updated in near real-time, and an archive mode that lets you fetch the headlines from a given moment in time. In both modes, the endpoint returns a JSON…