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/lemur47/logicnpx agentmods add skills/lemur47/logic/content-cadenceWrote 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/lemur47/logic/content-cadence)<a href="https://agentmods.dev/skills/lemur47/logic/content-cadence"><img src="https://agentmods.dev/badge/skills/lemur47/logic/content-cadence.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.03429 |
| Opus 5 | $0.00038 | $0.01715 |
| Sonnet 5 | $0.00015 | $0.00686 |
| Haiku 4.5 | $0.00008 | $0.00343 |
Grade A, and why
content-cadence 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 6d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Cadence
Every R&D artefact worth publishing feeds one post — a briefing or a deep dive, never both — and — where the calibration overlay puts social derivatives in scope — that post feeds one derivative. Drafting starts only once the sign-off owner has stated a content requirement; the artefact supplies the evidence, the requirement supplies the angle. This skill encodes the cadence, the two post frames, and the gates a draft must pass before it moves toward a public surface.
R&D artefact (PR, PoC, analysis)
↓
Content requirement (from the sign-off owner: angle, audience, expectation)
↓ choose ONE frame
Briefing | Deep Dive (EN + JA, same slug; diagrams/images where they clarify)
↓ PR = human-in-the-loop review gate
Social derivative (only if the overlay scopes it in; not committed)
This skill is organisation-neutral. Audience, voice, publishing channels, sign-off owners, and which artefact classes get a social derivative at all live in a gitignored calibration overlay, resolved by the three-rung lookup order — the same pattern as the anonymisation skill. The frames, gates, and conventions below are universal.
If the overlay is absent, do not halt: derive audience and voice from the existing posts in the blog content directory, treat the person requesting the draft as the sign-off owner, and flag the missing overlay in the handover so it gets created.
Inputs
Two inputs per run — an artefact and a requirement. Drafting needs both.
1. One R&D artefact. Acceptable inputs:
- A merged PR or shipped feature (link + diff context).
- A standalone PoC (
examples/directory or equivalent). - An analysis or investigation with a conclusion (retro finding, benchmark, calibration result).
If the artefact has no conclusion yet, stop — content follows the work, it does not precede it.
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.
- 6d ago First seen · 155 lines · 76 tokens per session scan A 7d30aad4f3b1
content-cadence is a skill published in the GitHub repository lemur47/logic (2 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 3,429 once invoked, about $0.0004 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
ib-collar
Generate tactical collar strategy reports for protecting PMCC positions through earnings or high-risk events. Requires TWS or IB Gateway running locally.
ib-portfolio-action-report
Generate a comprehensive portfolio action report with earnings dates and risk assessment. Use when user asks for portfolio review, action items, earnings risk, or position management across IB accounts. Requires TWS or IB Gateway running locally.
ib-trades-history
Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.
report-stock
Generate comprehensive stock analysis report (PDF or markdown) with trend, PMCC, and fundamental analysis.
ib-report-delta-adjusted-notional-exposure
Report delta-adjusted notional exposure across all IBKR accounts. Calculates option deltas using Black-Scholes and reports long/short exposure by account and underlying. Use when user asks about delta exposure, portfolio risk, or directional exposure.
ib-portfolio
Get portfolio positions from Interactive Brokers. Use when user asks about their portfolio, positions, holdings, or what stocks they own. Requires TWS or IB Gateway running locally.