Borrowing it
Nothing to install: this file belongs to AICMO/Autonomous-Agent-X-Bluesky. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AICMO/Autonomous-Agent-X-Bluesky/main/.claude/skills/commenting/SKILL.mdgit clone --depth 1 https://github.com/AICMO/Autonomous-Agent-X-BlueskyWrote 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/aicmo/autonomous-agent-x-bluesky/commenting)<a href="https://agentmods.dev/skills/aicmo/autonomous-agent-x-bluesky/commenting"><img src="https://agentmods.dev/badge/skills/aicmo/autonomous-agent-x-bluesky/commenting.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.03272 |
| Opus 5 | $0.00015 | $0.01636 |
| Sonnet 5 | $0.00006 | $0.00654 |
| Haiku 4.5 | $0.00003 | $0.00327 |
Grade A, and why
commenting 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 8d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commenting / Engagement Skill
Write valuable replies that build relationships and visibility
Why Commenting Matters
For accounts under 100 followers, commenting > original posts for growth. One viral reply = 12K impressions vs 400 from original post (30x). Reply-to-reply = 75x algorithm multiplier.
Queue-Delayed Replies (Critical Constraint)
Agent-created replies post hours to days late, killing algorithmic value.
Time decay: Replies lose 50% visibility every 6 hours. At 24h = ~6% visibility.
What works via queue: Reply-to-own only. Evergreen topics, no timing pressure.
What doesn't work: ALL outbound replies (brand accounts AND individuals). 62/62 outbound reply files failed at X API (403) in Week 9 audit — "not mentioned or engaged by the author." Brand accounts are NOT exempt. Zero confirmed working outbound reply targets.
Two types of replies — very different success rates:
Reply-to-own (your own tweet IDs): 100% SUCCESS RATE. Confirmed 2026-03-17: reply-20260317-003 and reply-20260317-004 both posted with HTTP 201. Replying to your own tweets works reliably. This is the primary engagement tactic.
Outbound replies to others: ~0% SUCCESS RATE. 62 reply files with valid numeric IDs failed at X API (403): "Reply to this conversation is not allowed because you have not been mentioned or otherwise engaged by the author." This is an X API permission restriction — you cannot reply to strangers' tweets via API until they have engaged with @tau_rho_ai first.
Breakdown of historical skipped files (2026-03-16 audit):
- 62 reply files (reply-*.txt) — valid numeric tweet IDs — failed at X API (403) — outbound to non-followers
- 9 reply files — invalid format (URL or @handle in REPLY_TO field) — failed at validation
- 19 tweet files (tweet-*.txt) — regular posts from early Feb 2026, likely duplicates
What works via API:
- Reply to your own tweets (100% success) — always use numeric tweet ID from workflow logs
- Reply to accounts that have previously @-mentioned or engaged with @tau_rho_ai (likely works, unconfirmed)
- Outbound to non-followers: Skip. Will always fail at API level.
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.
- 8d ago First seen · 278 lines · 30 tokens per session scan A d5a733136b7e
commenting is a skill published in the GitHub repository AICMO/Autonomous-Agent-X-Bluesky (11 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,272 once invoked, about $0.0002 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…