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 riasistemas/claude-channel-instagram --skill qualificationgit clone --depth 1 https://github.com/riasistemas/claude-channel-instagramWrote 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/riasistemas/claude-channel-instagram/qualification)<a href="https://agentmods.dev/skills/riasistemas/claude-channel-instagram/qualification"><img src="https://agentmods.dev/badge/skills/riasistemas/claude-channel-instagram/qualification/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/riasistemas/claude-channel-instagram/qualification"><img src="https://agentmods.dev/badge/skills/riasistemas/claude-channel-instagram/qualification.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 | $0.00049 | $0.00854 |
| Opus 5 | $0.00024 | $0.00427 |
| Sonnet 5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
qualification 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram qualification playbook
Trigger. Any channel notification with source="plugin:instagram:instagram". Inspect meta.kind to decide which path to take.
1. Inbound comment (meta.kind === "comment")
If meta.auto_dm === "true", do BOTH calls in the same response:
reply_comment(chat_id, comment_id, text)— public, brief (max ~12 words), one short sentence such as "Replied in DM 📩" or the equivalent in your locale. Never copy the user's text or sound robotic.send_private_reply(comment_id, text)— private DM opener that:- Greets by
meta.crm_nameif an extension provided one, else by@username. - References ONE concrete signal from the comment (their question, the post topic).
- Ends with a single, short qualifying question.
- Length: 1–2 sentences. No decorative emojis.
- Greets by
If meta.auto_dm is absent/false, only reply_comment is appropriate (the operator opted out of the DM bridge).
2. Inbound DM (meta.kind === "dm")
This is the conversation thread. Treat it like any chat surface:
- Use
send_dm(chat_id, text|image_path|audio_path)to reply. - Keep messages short (1–3 sentences). Instagram doesn't render markdown tables, so use plain text or short lists.
- If
meta.transcriptis present, the user sent audio — read the transcript and reply in kind. - If
meta.image_pathis present, use the Read tool on the path before replying so the response references what they sent.
The qualification cadence (what to ask, in what order, when to escalate) is intentionally NOT prescribed here — every operator has their own funnel. Document yours in CLAUDE.md or in your private extensions.
3. Window restrictions you must respect
- 24h DM window: free-form replies only within 24h of the user's last DM. After that,
send_dmreturns an error. The plugin core does not implement theHUMAN_AGENTtag yet (that's reserved for a future minor release behind an opt-in flag); don't try to bypass. - Private reply window: 7 days from the comment, one DM per comment. If you've already opened DM via the comment, switch to
send_dmfor follow-ups. - Hours: respect any business-hours rule the operator has configured (defaults vary). Inbound replies are always ok.
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 · 59 lines · 49 tokens per session scan A d26342fd27ec
qualification is a skill published in the GitHub repository riasistemas/claude-channel-instagram (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 854 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…