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 agentmods add commands/suboss87/fdeops/receiptsgit clone --depth 1 https://github.com/suboss87/FDEOpsWhat 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 | $0.00014 | $0.00255 |
| Opus 5 | $0.00007 | $0.00128 |
| Sonnet 5 | $0.00003 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
receipts 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 2d 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
Load @fde (skills/fde/SKILL.md). Situation: when did we agree?
If fde resume shows NO ENGAGEMENT: ask "What should we call this client?" once, then you run fde resume --init. Never tell the human to type the CLI.
Do not argue from chat memory. Search the record.
Run fde receipts <term> (fallback: npx --yes fdeops receipts <term>). Use the term the human named - topic, person, deliverable, or date window.
Answer with dated receipts: who said it, when, and where it lives in .fde/. No reference file needed unless the hit spans multiple files.
No hit is a gap, not proof. Say so plainly and ask one question that would close the gap.
Do not invent meetings, quotes, or commitments. If the record is silent, the answer is "not in the record yet."
Done when: you have cited dated receipts for the term or named the specific gap to fill.
Not for TypeScript errors, unit tests, refactors, or git commits - those stay in the host agent.
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.
- 2d ago First seen · 22 lines · 14 tokens per session scan A 1d1d49689a5a
receipts is a command published in the GitHub repository suboss87/FDEOps (213 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 255 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
crossframe-essay
使用 CrossFrame Essay 把用户给出的主题、素材或问题写成中文批判性洞察文章。.
crossframe-max
Use CrossFrame Max only when the user explicitly asks for maximum CrossFrame mode, exhaustive structural projection, full-scale world-model interpretation, or no word-limit complete explanation.
crossframe-audit
使用 CrossFrame 做高责任、反俘获、强判断或 v5.0 覆盖审计。适合处分、名誉、权利、资源、公共记忆、AI 合规材料、框架边界和“有没有概念缺失”的问题。.
crossframe-promax
PROMAX-NAMED-ONLY：只有 crossframe-promax、CrossFrame ProMax、$crossframe-promax、/crossframe-promax 四种明确名称具有触发权。.
crossframe-suite
Use this command when a CrossFrame task needs multiple sibling skills in sequence.
crossframe-history
Use CrossFrame History for historical materials, civilization continuity, source-ledger boundaries, dynasty or institutional history, archive-access backlog, FOIA closeout, or local C5 boundary summaries.