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 agentmods add skills/tokenbender/agent-guides/blade-and-contractnpx skills add tokenbender/agent-guides --skill blade-and-contractgit clone --depth 1 https://github.com/tokenbender/agent-guidesWrote 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/tokenbender/agent-guides/blade-and-contract)<a href="https://agentmods.dev/skills/tokenbender/agent-guides/blade-and-contract"><img src="https://agentmods.dev/badge/skills/tokenbender/agent-guides/blade-and-contract.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01005 |
| Opus 5 | $0.00034 | $0.00502 |
| Sonnet 5 | $0.00014 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
blade-and-contract 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blade and Contract
Use this skill to make language dangerous without making it sloppy.
The core method is simple:
Lead with the blade. Anchor with the contract.
The blade is the sentence that creates attention, discomfort, and a fight. The contract is the operational definition, boundary, protocol, or receipt that makes the sentence true under the intended frame.
Operating Posture
Do not default to timid epistemic humility when the user wants aggro-pull. Preserve provocation when it is strategic. The aim is not to avoid objections; it is to choose objections that drag readers into the user's ontology.
Treat definitional fights as territory, not paperwork. If a reader objects to a word, ask whether that objection exposes an old or weak category. Make the response force the critic to argue inside the user's frame.
Keep the claim bold at the level of concept and exact at the level of operation.
Workflow
-
Identify the blade.
- What sentence would make the target reader stop, object, quote, or argue?
- Keep it short enough to travel.
- Prefer category-shifting language: "X is not Y; X only counts when Z."
-
Identify the contract.
- Define the object, denominator, intervention, protocol, metric, scope, or constraint that makes the blade defensible.
- Do not apologize for the contract. State it as the battlefield.
- Convert caveats into doctrine: "This is not a weakness; this is the object we are isolating."
-
Redirect objections.
- Do not soften merely because an objection is predictable.
- Ask whether the objection is actually bait: can it be turned into "you are using the wrong definition"?
- Make the critic choose between accepting the contract or explicitly arguing for a narrower ontology.
-
Remove weak attack surfaces.
- Cut ambiguity that lets critics attack a claim the user did not mean.
- Preserve ambiguity that usefully pulls attention only if the follow-up contract snaps shut.
- Replace loose hype with precise provocation.
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.
- 6d ago First seen · 114 lines · 68 tokens per session scan A 2225a6041b83
blade-and-contract is a skill published in the GitHub repository tokenbender/agent-guides (368 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…