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 ahmedtawfeeq1/loredex --skill loredex-productgit clone --depth 1 https://github.com/ahmedtawfeeq1/loredexWrote 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/ahmedtawfeeq1/loredex/loredex-product)<a href="https://agentmods.dev/skills/ahmedtawfeeq1/loredex/loredex-product"><img src="https://agentmods.dev/badge/skills/ahmedtawfeeq1/loredex/loredex-product/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/ahmedtawfeeq1/loredex/loredex-product"><img src="https://agentmods.dev/badge/skills/ahmedtawfeeq1/loredex/loredex-product.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 | $0.00080 | $0.00468 |
| Opus 5 | $0.00040 | $0.00234 |
| Sonnet 5 | $0.00016 | $0.00094 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
loredex-product 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 12d 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.
What it actually says
/loredex-product
npx -y loredex@latest curate --product [--objective "<text>"] [--refresh-stale] [--dry-run] [-y]
Ask the objective first if the user has one (steers the narrative); without it the LLM derives the product's objective from the material.
What one run does:
- Pulls the dex remote so teammates' latest notes and handoffs are included.
- Deterministic dashboard (works with
--no-llmtoo): per-project state table (notes, last activity, active topics, stale counts, Start-Here-brief freshness), the flow table of open/consumed handoffs between teams with age, and cross-project reference edges. - LLM reduce over the per-project Start Here briefs + recent notes: product narrative, one-line state + next step per project, a cross-project reading order, and report-only risks/contradictions and duplicate-coverage findings (e.g. two projects describing the same API field differently). Nothing is auto-stamped across project boundaries — surface the findings to the user and let them judge.
- Writes
Start Here - Product.mdat the dex root (linked from the Home index), commits, and pushes.
--refresh-stale re-curates any project whose own brief is missing or older than its
newest note before the reduce — use it when the per-project briefs haven't been kept up.
Cost note: unchanged projects reuse their existing briefs, so runs are incremental.
Show the dashboard + any risks/duplicates to the user with --dry-run first, then apply
with -y after they confirm — same choreography as every other loredex write.
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.
- 12d ago First seen · 35 lines · 80 tokens per session scan A e898f949acb7
loredex-product is a skill published in the GitHub repository ahmedtawfeeq1/loredex (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 468 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
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.
implement-task
Pick up and work on a binder Task — investigate bugs, discuss open questions, design solutions, write tests, or implement code. Use when asked to "work on", "pick up", "implement", or "fix" a task.
daily-brief
Narrate FKF's deterministic daily control surface. Use when an owner asks to prepare the day, get a daily brief, or identify today's priorities and collection gaps.