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.
git clone --depth 1 https://github.com/EditorialOS/pinterest-marketing-strategistWrote 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/commands/editorialos/pinterest-marketing-strategist/track)<a href="https://agentmods.dev/commands/editorialos/pinterest-marketing-strategist/track"><img src="https://agentmods.dev/badge/commands/editorialos/pinterest-marketing-strategist/track/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/commands/editorialos/pinterest-marketing-strategist/track"><img src="https://agentmods.dev/badge/commands/editorialos/pinterest-marketing-strategist/track.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 | $0.00054 | $0.02500 |
| Opus 5 | $0.00027 | $0.01250 |
| Sonnet 5 | $0.00011 | $0.00500 |
| Haiku 4.5 | $0.00005 | $0.00250 |
Grade A, and why
track 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 11d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/track
Log results. Learn from them. Next batch gets smarter.
Pinterest pins live for months. A pin that looks weak at 7 days may be strong at 60. The learning loop accounts for this with multiple tracking windows.
Trigger
Use after pins have been live for 7+ days. Run again at 30 days for the full picture. Works with a batch name, individual pin data, or a Pinterest analytics export.
Inputs
- Batch name or pin topic — which pins to track (required)
- Results — impressions, saves, clicks, close-ups per pin. Accepts any format: Pinterest analytics CSV, manual entry, summary numbers, even partial data ("Pin 1 got 200 saves, the rest got about 30 each")
- Notes — optional. "Pin 3 got repinned by a content strategist," "The diagram pin got high saves but low clicks."
- Time period — optional. Default: since posted. Can specify: "7-day check" or "30-day review."
Don't block on perfect data. Partial data is still useful.
Step 1 — Gather Results
Accept Pinterest analytics in any format:
- Pinterest analytics export (CSV or pasted)
- Manual entry per pin (impressions, saves, clicks, close-ups, outbound clicks)
- Summary numbers for the batch
- Partial: "Pin 1 did great, the rest were average"
Key Pinterest metrics:
- Impressions — times the pin appeared in feeds and search
- Saves — users saving to their boards (strongest signal — compounds over time)
- Pin clicks / close-ups — users tapping to see the pin larger
- Outbound clicks — users clicking through to the destination URL (the traffic metric)
- Engagement rate — (saves + clicks) / impressions
Step 2 — Compare to Prediction
Pull the prediction from the batch record saved during /create.
- Within 15%: accurate prediction. Note what held.
- Over 15% above: outperformed. Identify what was different.
- Over 15% below: underperformed. Identify what was different.
If no prediction existed (first batch): this establishes the baseline.
Pinterest timing caveat: If tracking at 7 days, note: "Pinterest's algorithm distributes pins slowly. A 7-day read may understate long-term performance. Run /track again at 30 days for the full picture."
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.
- 11d ago First seen · 294 lines · 0 tokens per session scan A a609e9f00d31
track is a command published in the GitHub repository EditorialOS/pinterest-marketing-strategist (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 2,500 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 2026-08-31.
Other commands, from other repositories
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
autonomy
Set Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto) — how much the agent does before asking. Use with a number, +/- to cycle, or no argument to show current.
level
Deprecated alias for /hmd:autonomy. Sets Heimdall autonomy (1=Guided, 2=Checkpoint, 3=Full Auto). Still works; prints a one-line rename notice.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
dashboard
Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.