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 kriscard/Skills --skill tweet-todaygit clone --depth 1 https://github.com/kriscard/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/kriscard/skills/tweet-today)<a href="https://agentmods.dev/skills/kriscard/skills/tweet-today"><img src="https://agentmods.dev/badge/skills/kriscard/skills/tweet-today/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/kriscard/skills/tweet-today"><img src="https://agentmods.dev/badge/skills/kriscard/skills/tweet-today.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 | $0.00061 | $0.01656 |
| Opus 5 | $0.00030 | $0.00828 |
| Sonnet 5 | $0.00012 | $0.00331 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
tweet-today 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 10d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tweet Today
Turn available context into categorized tweet options the user can choose from today: specific, peer-level, and non-cringe.
Boundary
Default to at least 3 single-tweet options under 280 characters, grouped by category. Do not create a thread, LinkedIn post, or blog outline unless the user asks. Never claim the tweet was posted; this skill only drafts.
If the user asks for a longer essay, use the blog skill. If they ask for a daily standup, use the standup skill.
Workflow
1. Harvest receipts
Use the nearest available source first, then extract concrete receipts:
| Branch | Source |
|---|---|
| Conversation | Current visible conversation, agent session, or pasted transcript |
| Today | User-provided bullets about today's work; if missing, ask for them or permission to inspect notes/git |
| Topic | The named topic plus any opinion, lesson, or example already provided |
| Draft | The user's rough tweet or idea |
| Structured receipt | A public-safe receipt promoted by capture-receipt or close-day, including proof and private source backlinks |
Receipts are shipped changes, bugs fixed, screenshots, code snippets, tools tried, decisions made, mistakes noticed, or opinion shifts.
Complete when the source can support 3 distinct tweet options. For a full-day request, aim for 3-5 receipts. If the source lacks subject, stance/lesson, or a concrete receipt, do a mini-grill before drafting.
2. Mini-grill thin context
Ask only the smallest set of questions needed to make the tweet real. Prefer these, adapted to the source:
- What changed your mind today?
- What did you actually do, build, debug, or notice?
- What is the non-obvious lesson?
- Who should care, and what should they do differently?
- What concrete receipt proves it?
- Are there Twitter/X accounts whose style should inspire this batch?
Complete when the answer can support categorized tweets without inventing facts.
3. Safety gate
Scan the source before drafting. Remove or generalize anything unsafe: secrets, credentials, tokens, API keys, private URLs, private repo names, customer data, unreleased metrics, .env values, config values, or copied logs.
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.
- 10d ago First seen · 155 lines · 61 tokens per session scan A e6aa68f4d9d0
tweet-today is a skill published in the GitHub repository kriscard/Skills (14 stars, last pushed 29d ago), licensed MIT. It adds 61 tokens to every session and 1,656 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
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…
aidlc-master
Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in aidlc-docs/. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for…
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
security-specialist
Runs security audits on codebases — full scans, diff reviews, threat models, vulnerability triage, remediation guidance, and finding tracking. Activate when the user says "security scan", "audit this repo", "review this PR for security", "threat model", "triage vulnerabilities", "fix this vuln", or "track findings".
ralph-loop-kiro-specs
Automated iterative agent runner for spec-based development in Kiro. Wraps kiro-cli in a self-correcting bash loop that picks up tasks from a Kiro spec, implements them one at a time, verifies against exit criteria, and accumulates corrections and codebase patterns across iterations. Use this skill when the user…