Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/linkedin-archiveWrote 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/mishahanin/heading-os/linkedin-archive)<a href="https://agentmods.dev/skills/mishahanin/heading-os/linkedin-archive"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/linkedin-archive/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/mishahanin/heading-os/linkedin-archive"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/linkedin-archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 114 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00068 | $0.01208 |
| Opus 5 | $0.00034 | $0.00604 |
| Sonnet 5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
linkedin-archive 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Archive
Move a just-published LinkedIn piece from staging (outputs/content/linkedin/ plus optional explicit images) into the typed datastore archive (datastore/content/linkedin-archive/{articles|posts|comments}/{slug}/).
Script: scripts/linkedin-archive.py.
Workflow
1. Resolve type if needed
If the staged file's name does not contain _linkedin-(post|article|comment)_ and no type: frontmatter is set, ask the CEO via AskUserQuestion:
- Post
- Article
- Comment
Pass the answer to the script as --type <choice>.
2. Resolve images if any
Ask the CEO via AskUserQuestion:
- No image
- One image
- More than one
If "One image" or "More than one": send a follow-up plain-text turn, "Reply with the path(s) to the image(s)". Wait for the CEO's free-form reply, one path per line. AskUserQuestion is multiple-choice only, so path collection always happens in a separate text turn.
Pass each image as a separate --image <path> argument. Default is no image.
3. Dry-run
python scripts/linkedin-archive.py [--slug <slug>] [--type <type>] [--image <path>]...
Exit codes that need handling:
2: nothing found - tell the CEO and stop.3: destination conflict - surface the existing folder, ask how to proceed.5: type still ambiguous - re-ask.6: image path does not exist - re-ask.7: source untracked - tell CEO togit add, then retry.
4. Confirm
Show the plan. Ask via AskUserQuestion:
- Approve and execute (with auto-commit)
- Approve and execute (no commit)
- Cancel
Wait for explicit approval.
5. Execute
python scripts/linkedin-archive.py [...flags] --execute [--commit]
6. Confirm done
Report destination folder, files moved (count), and the commit hash if --commit was used.
Undo
The script does not provide an --undo flag. To revert a wrong move:
- If
--commitdid NOT fire:git mvfiles back manually, thenrmdirthe empty destination folder. - If
--commitfired and nothing else has been committed since:git reset --hard HEAD~1. Verifygit statusfirst; this is destructive. - If exit code 8 (
--commitran but auto-commit failed): files are moved and staged in the index, but no commit landed. Either inspect the failure (often a pre-commit hook), fix it, and rungit commitmanually; orgit restore --staged <paths>to unstage and decide what to do next. - If exit code 9 (git command timed out): a timeout before any
git mvleaves the disk untouched. If the timeout fires mid-sequence, rungit statusto see what was already moved, andgit mvback as needed.
What ships with it
5 files 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 · 128 lines · 68 tokens per session scan A 624583ea12f0
linkedin-archive is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 1,208 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
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.