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/x-pulseWrote 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/x-pulse)<a href="https://agentmods.dev/skills/mishahanin/heading-os/x-pulse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/x-pulse/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/x-pulse"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/x-pulse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 15 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 | $0.00155 | $0.02626 |
| Opus 5 | $0.00077 | $0.01313 |
| Sonnet 5 | $0.00031 | $0.00525 |
| Haiku 4.5 | $0.00015 | $0.00263 |
Grade A, and why
x-pulse 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Pulse - X.com Account-Monitoring Intelligence
Scan a curated, categorised list of X.com accounts and surface what they posted in the last 72h (configurable). Deliver an intelligence brief with 31C relevance and concrete actions.
Variables
window: [optional] 24h | 72h (default) | 7d
bucket: [optional] one category from config/x-pulse-accounts.yaml; if omitted, all categories scanned
max_per_account: [optional] tweets to fetch per handle (default 30, max 100)
dry_run: [optional] print plan + estimated cost, exit without API call
Pre-flight
/x-pulse does NOT use a browser and does NOT hit X.com from this workspace's IP. Apify runs the scraping server-side. Therefore:
- VPN preflight rule does NOT apply.
- Comet rule applies only by absence (no browser involved).
The skill checks for APIFY_TOKEN in .env. If missing:
- Halt
- Print: "Apify token not found. Sign up at https://apify.com (free tier = $5/month credit), then add
APIFY_TOKEN=apify_api_xxxto.env. Re-run /x-pulse when ready." - Exit cleanly.
Phase 0: Setup
- Parse user options. Default:
--window 72h, all buckets,--max-per-account 30. - Compute the output directory. The brief is a DATA artifact -- it must land in the DATA overlay,
never the engine tree.
pulse.pywrites--output-dirliterally relative to cwd (the engine root after thecd). Resolve an absolute path under the data outputs dir:
Usecd "$(git rev-parse --show-toplevel)" OUTPUTS_DIR="$(python3 -c "import sys; sys.path.insert(0,'.'); from scripts.utils.workspace import get_outputs_dir; print(get_outputs_dir())")" out_dir="$OUTPUTS_DIR/intel/x-pulse/YYYY-MM-DD-HHMM" # timestamp to the minute; on-demand may run several times a day$out_dir(or its resolved value) for--output-dirin every command below. Never pass a bareoutputs/intel/x-pulse/...-- that resolves into the engine. - Run
pulse.pyin dry-run mode FIRST and present the plan to the user:
cd "$(git rev-parse --show-toplevel)" && python ".claude/skills/x-pulse/scripts/pulse.py" --dry-run \
--window <window> [--bucket <bucket>] \
--max-per-account <N> \
--output-dir $out_dir
What ships with it
4 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.
- 9d ago First seen · 269 lines · 155 tokens per session scan A 3d1e72283305
x-pulse is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 155 tokens to every session and 2,626 once invoked, about $0.0008 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 2026-09-03.
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-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-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-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.