Canghe Post To X
freestylefly/canghe-skills
Posts content and articles to X (Twitter). An agent skill from freestylefly/canghe-skills.
Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the…
Install Blade And Contract
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tokenbender/agent-guides blade-and-contract --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-skills/blade-and-contract .claude/skills/blade-and-contract && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .claude/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contractType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tokenbender/agent-guides blade-and-contract --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-skills/blade-and-contract .agents/skills/blade-and-contract && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .agents/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tokenbender/agent-guides blade-and-contract --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-skills/blade-and-contract .cursor/skills/blade-and-contract && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .cursor/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tokenbender/agent-guides.git --path claude-skills/blade-and-contract--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tokenbender/agent-guides blade-and-contract --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-skills/blade-and-contract .gemini/skills/blade-and-contract && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .gemini/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tokenbender/agent-guides blade-and-contractInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-skills/blade-and-contract .github/skills/blade-and-contract && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .github/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tokenbender/agent-guides --skill blade-and-contract -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tokenbender/agent-guides blade-and-contract --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tokenbender/agent-guides.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-skills/blade-and-contract .opencode/skills/blade-and-contract && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "blade-and-contract" agent skill from https://github.com/tokenbender/agent-guides/tree/main/claude-skills/blade-and-contract into .opencode/skills/blade-and-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "blade-and-contract", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
blade-and-contract- GitHub stars
- 367
- Token cost
- ~1.2k tokens
- SKILL.md length
- 669 words
- Files
- 2
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the…
- Works in 5 steps: Identify the blade. → Identify the contract. → Redirect objections. → …
- Tasks that involve Social media posts
- SKILL.md covers Operating Posture, Workflow, Voice Rules and Review Lens, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Blade And Contract is an agent skill from tokenbender/agent-guides. Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the user wants provocative attention-pull, category-defining language, or aggressive devil's-advocate defense without losing operational defensibility.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Marketing & SEO, covering Social media posts and Proposals and quotes. The repository describes itself as: one page guides that i let my subscribed/customised agents consume to perform actions. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Social media posts
- Tasks that involve Proposals and quotes
Example prompts
- “/blade-and-contract”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Identify the blade.
- Identify the contract.
- Redirect objections.
- Remove weak attack surfaces.
- Make disagreement expensive.
What it can do on your machine
Read from SKILL.md and the folder at commit a74dd9d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Blade And Contract loads about 1.2k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 669 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from tokenbender/agent-guides at commit a74dd9d, republished under its Apache-2.0 licence (© tokenbender). 669 words, ~1,199 tokens.
Download SKILL.mdSave it as
.claude/skills/blade-and-contract/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- blade-and-contract
- description
- Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the user wants provocative attention-pull, category-defining language, or aggressive devil's-advocate defense without losing operational defensibility.
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.
Make disagreement expensive.
- A good claim should require paragraphs to attack, not one dismissive sentence.
- Force any serious rebuttal to repeat the user's terms, definitions, and frame.
Voice Rules
Use direct, charged language:
- "The old category is too small."
- "This is the bar."
- "Under this contract, the result exists."
- "If you want a different contract, name it and run the experiment."
- "The caveat is not a retreat; it is the definition."
Avoid folded-shoulder language when the user asks for force:
- Avoid "maybe", "somewhat", "preliminary", "we humbly suggest" unless the uncertainty is strategically useful.
- Avoid hiding behind "to our knowledge" when a sharper field-level standard can be named.
- Avoid caveat-dumps before the reader knows why the claim matters.
Show full SKILL.md (239 more words)Show less
Review Lens
When reviewing text, classify issues this way:
- Good aggro: provocative, high-attention, defensible under the stated contract. Preserve or intensify it.
- Bad aggro: provocative but easy to kill because the contract is missing, wrong, or inconsistent. Add the contract rather than making the claim timid.
- Timid truth: accurate but forgettable. Add a blade.
- Loose grandiosity: big words with no operational core. Replace with a sharper claim and receipt.
Generic Patterns
Instead of:
This may be a new way to think about evaluation.
Use:
The old evaluation target is the easier problem. We change the success condition.
Then define the contract:
Here, success means the system survives the stated intervention, not merely that it scores well in the untouched setting.
Instead of:
This is not a complete replacement for the original system.
Use:
It is not a replacement system. That is the point: it isolates the causal substrate while the scaffold is held fixed.
Instead of:
Critics might say this definition is too narrow.
Use:
If the objection requires changing the object, then it is not a refutation of the result. It is a demand for a different experiment.
Final Check
Before finishing any Blade-and-Contract work, ensure:
- The main claim has a blade.
- The key term has an operational contract.
- The caveat has been turned into a boundary, not an apology.
- The most obvious objection pulls the reader deeper into the frame.
- The final wording sounds authored, not committee-approved.
© tokenbender, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in claude-skills/blade-and-contract of tokenbender/agent-guides.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit a74dd9d
Compare with similar skills
Blade And Contract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Blade And Contract this skilltokenbender/agent-guides | 367 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Canghe Post To Xfreestylefly/canghe-skills | 461 | 4 repos | ~1.7k | Automated safety check: Warn | None | |
| Getxapi ConnectLeoYeAI/openclaw-marketing-skills | 1k | 1 repos | ~715 | Automated safety check: Pass | Custom licence | |
| Anti Vibe Writingweijt606/anti-vibe-writing | 119 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Tnr Content Auditstudie-tech/TheNinjaRPG | 104 | — | ~4.9k | Automated safety check: Notes | None | |
| Collaborating With Geminiyunshenwuchuxun/latex-paper-skills | 265 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Getxapi Connect
LeoYeAI/openclaw-marketing-skills
Connect GetXAPI to pull public X/Twitter marketing signals into OpenClaw workflows.
Anti Vibe Writing
weijt606/anti-vibe-writing
A skill your agent uses when the user wants to humanize, de-AI, polish, or warm up an AI-generated document, in English or Chinese.
Tnr Content Audit
studie-tech/TheNinjaRPG
Audit TheNinja-RPG game content (jutsu, items, bloodlines, quests, badges, AI characters, assets) for grammar, balance, sound, animation, visual and consistency gaps, and write suggestions for the…
Collaborating With Gemini
yunshenwuchuxun/latex-paper-skills
Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero.
Ops Socials
Lifecycle-Innovations-Limited/claude-ops
OPS on-demand: This skill should be used when the user asks to "tweet", "post to linkedin", or…
More from tokenbender/agent-guides
All 11 skills in this repoCapability Horizon Estimator
tokenbender/agent-guides
Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling.
Technical Writing Workflow
tokenbender/agent-guides
A skill your agent uses for planning, researching, drafting, revising, or auditing technical write-ups, textbooks, papers, reports, READMEs, research notes, PR narratives, and public technical prose.
Epistemic Libido
tokenbender/agent-guides
Filter, compare, and rank papers, posts, captures, threads, bookmarks, product claims, or research ideas for high-entropy mechanistic insight and underpriced leverage.
Manim Math Explainer
tokenbender/agent-guides
Trigger when: (1) the user asks for Manim, Manim Community, or ManimCE, (2) code contains from manim import , or (3) the task is to build a mathematical explainer animation.
Worklog
tokenbender/agent-guides
Issue-led atomic work logging. An agent skill from tokenbender/agent-guides.
X Thread Reader
tokenbender/agent-guides
A skill your agent uses when the user provides an X/Twitter status URL and needs the full thread, context beyond the first post, comparison, summary, intent analysis, title extraction, or reliable…
Related
Questions about Blade And Contract
What does Blade And Contract do?
Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the…. Blade And Contract is an agent skill from tokenbender/agent-guides. Use as Codex's default rhetoric backbone when writing, reviewing, naming, positioning, debating, or sharpening papers, proposals, essays, launches, social posts, narratives, and claims where the user wants provocative attention-pull, category-defining language, or aggressive devil's-advocate defense without losing operational defensibility.
When should I use Blade And Contract?
Blade And Contract fits situations like: tasks that involve Social media posts; tasks that involve Proposals and quotes.
How do I install Blade And Contract in Claude Code?
Run `npx skills add tokenbender/agent-guides --skill blade-and-contract -a claude-code`. Or copy the skill folder (claude-skills/blade-and-contract in tokenbender/agent-guides) into .claude/skills/blade-and-contract in your project. Claude Code loads it when a task matches its description.
How do I install Blade And Contract in Codex?
Run `npx skills add tokenbender/agent-guides --skill blade-and-contract -a codex`. Or copy the skill folder (claude-skills/blade-and-contract in tokenbender/agent-guides) into .agents/skills/blade-and-contract in your project. Codex loads it when a task matches its description.
Can I use Blade And Contract in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tokenbender/agent-guides --skill blade-and-contract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blade-and-contract, .gemini/skills/blade-and-contract, .github/skills/blade-and-contract and .opencode/skills/blade-and-contract in your project.
What does Blade And Contract need to run?
SKILL.md names no scripts, command-line tools or credentials: Blade And Contract is instructions for the agent only.
Does Blade And Contract access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Blade And Contract safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Blade And Contract use?
Blade And Contract is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Blade And Contract use?
About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Blade And Contract?
Skills that share tags, products or a category with Blade And Contract: Canghe Post To X (freestylefly/canghe-skills, 461 stars), Getxapi Connect (LeoYeAI/openclaw-marketing-skills, 1k stars), Anti Vibe Writing (weijt606/anti-vibe-writing, 119 stars) and Tnr Content Audit (studie-tech/TheNinjaRPG, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Blade And Contract?
tokenbender (a GitHub user) maintains it in tokenbender/agent-guides, which has 367 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 23, 2026.
Source: tokenbender/agent-guides on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.