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 synaptiai/synapti-marketplace --skill llm-operator-principlesgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/llm-operator-principles)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/llm-operator-principles"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/llm-operator-principles/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/synaptiai/synapti-marketplace/llm-operator-principles"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/llm-operator-principles.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 | $0.00148 | $0.01161 |
| Opus 5 | $0.00074 | $0.00580 |
| Sonnet 5 | $0.00030 | $0.00232 |
| Haiku 4.5 | $0.00015 | $0.00116 |
Grade A, and why
llm-operator-principles 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 today.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Operator Principles
Consulted by every /flow:* command before any other skill.
Iron Law
CONVERGENCE = ZERO FINDINGS. NOT EXHAUSTED BUDGET.
Iteration ceilings (fixForwardMaxIterations, reviewCycleLimit, qualityCheckMaxIterations, closedLoop.maxDebugIterations) are safety nets against infinite loops, not planned stop points.
You Are An LLM Agent
Iteration is cheap, you do not tire, work is measured in tool calls, not human-engineer time.
Calendar-Time Estimates Are Prohibited
Never write, suggest, or imply estimates in calendar units (weeks, days, hours, sprints, ETAs, deadlines). Phrases like "multi-day effort" or "by Friday" must never appear in any output: PR bodies, journal entries, commit messages, AskUserQuestion bodies, escalations, follow-up issues. If size must be conveyed, use t-shirt sizing (S / M / L), only when the user asked; otherwise describe the work ("3 file edits + a test re-run").
Default Finding Disposition: Fix In This PR
Every finding (P1/P2/P3) from any review is fixed in this PR. The ONLY non-fix outcomes:
- It requires a user product decision Claude cannot make (true ambiguity, not triage).
- It is in a binary, vendored, generated, or third-party file Claude does not own.
- The fix requires modifying a dependency Claude does not own: open an upstream issue, document the workaround in-PR.
- The user invoked minimal-scope mode for this run (below).
Everything else (P3 in untouched files, "out-of-scope" findings, findings "not required by acceptance criteria"): fix now (improve: commit if needed). Finding triage is NEVER a valid escalation trigger; if drafting a Situation/Tried/Options block about a finding, stop and fix it.
Multi-PR Sequencing Is The User's Call
Default to ONE PR. Split only when the user asks, the work crosses a deployment boundary (migration before code), or findings need user product decisions between phases; never to reduce reviewer load or defer findings.
Iteration Ceiling Semantics
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.
- today Changed · -91 lines · -7 tokens per session e2f886e743f5
- 7d ago First seen · 167 lines · 155 tokens per session scan A cffcc9d098ff
llm-operator-principles is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 148 tokens to every session and 1,161 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
create-or-update-concepts
Scan and analyze the project codebase to create or update concept files in agents-context/concepts/ (organized by domains/, source/, shared/) and update the README index and Load-When Cheatsheet.
step2-scope-tasks
Break a specification into ordered task groups with explicit context-awareness directives.
step1-write-spec
Gather requirements through structured Q&A, then formalize into a specification document.
create-pr
Creates a GitHub Pull Request on the current branch with a description focused on WHAT changed (not HOW). Uses emojis in the title and description. Use when the user asks to create a PR, open a pull request, or submit changes for review. Triggers on mentions of PR, pull request, merge request, or code review.
step4-archive-spec
Archive a completed spec — moves it to specs-archived and blocks agent access.
plan-product
Define product mission, vision, target users, and technology stack.