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 IvanBBaev/instagram-mcp --skill instagram-weekly-reportgit clone --depth 1 https://github.com/IvanBBaev/instagram-mcpWrote 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/ivanbbaev/instagram-mcp/instagram-weekly-report)<a href="https://agentmods.dev/skills/ivanbbaev/instagram-mcp/instagram-weekly-report"><img src="https://agentmods.dev/badge/skills/ivanbbaev/instagram-mcp/instagram-weekly-report/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/ivanbbaev/instagram-mcp/instagram-weekly-report"><img src="https://agentmods.dev/badge/skills/ivanbbaev/instagram-mcp/instagram-weekly-report.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 | $0.00066 | $0.00735 |
| Opus 5.5 | $0.00026 | $0.00294 |
| Sonnet 5.5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
instagram-weekly-report 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram performance report
A read-only workflow over this server's account, media and insights tools. It never publishes, comments, replies, hides or deletes anything.
Inputs
- Period: the number of days to cover, 1-30. Default 7 when the user does not say.
- Account: a configured account profile name. When the user names one, pass
account: "<name>"in every tool call; otherwise omitaccountand the default profile is used.
Steps
- Call
instagram_get_accountfor the account name, username and follower count. Put them in the report heading. - Work out the period as Unix seconds:
untilis now,sinceisuntilminus the period in days times 86400. Instagram keeps 90 days of insights, so a period of 30 days or less is always inside the window. - Call
instagram_get_account_insightswithsinceanduntil. Leavemetricsout to get the default post-2025 set (views, reach, accounts_engaged, total_interactions, likes, comments, shares, saves, replies, follows_and_unfollows, profile_links_taps). A metric listed inmissingMetricshad no data: it is absent, not zero, so say so instead of reporting 0. - Call
instagram_list_media. It returns the newest media first, one page by default. Keep the items whosetimestampfalls inside the period. If every item on the page is inside the period andpaging.afteris present, call it again withafterset to that cursor until an item older than the period appears. - For each post kept in step 4, call
instagram_get_media_insightswithmedia_idset to the item'sid. Passmedia_product_type(FEEDorREELS) when the media item carries it, so the right default metric set is used. - Write the report:
- headline account metrics for the period, with the follower count;
- a table of the period's posts: date, type, a short caption excerpt, views, reach, likes, comments, saves, shares;
- the best and the weakest post, and what sets them apart;
- two or three concrete, specific suggestions for the next period.
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.
- 9d ago First seen · 60 lines · 66 tokens per session scan A 4a02b9c7255b
instagram-weekly-report is a skill published in the GitHub repository IvanBBaev/instagram-mcp (7 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 735 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-28.
instagram-weekly-report compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| instagram-weekly-reportIvanBBaev/instagram-mcp | Skill | 7 | 8d ago | MIT | A | 66 | Claude Code, Codex |
| instagram-apiericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 91 | Claude Code, Codex |
| ibrahim-content-draftsS3YED/appie-kit | Skill | 14 | 2mo ago | MIT | A | 43 | Claude Code, Codex |
| instagram-apifetcher-sh/fetcher-skills | Skill | 2 | 2mo ago | MIT | A | 153 | Claude Code |
| instagram-scraperjeniok/skills | Skill | 0 | 2mo ago | MIT | A | 148 | Claude Code, Codex |
| instagram-searchXPOZpublic/xpoz-clawhub-skills | Skill | 6 | 1mo ago | none | A | 47 | Claude Code, Codex |
| instagram-scraperskillify-sh/skills | Skill | 0 | 2mo ago | MIT | A | 148 | Claude Code, Codex |