Borrowing it
Nothing to install: this file belongs to khaoss85/agent-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/khaoss85/agent-crm/main/.agents/skills/build-signature-order/SKILL.mdgit clone --depth 1 https://github.com/khaoss85/agent-crmWrote 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/khaoss85/agent-crm/build-signature-order)<a href="https://agentmods.dev/skills/khaoss85/agent-crm/build-signature-order"><img src="https://agentmods.dev/badge/skills/khaoss85/agent-crm/build-signature-order/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/khaoss85/agent-crm/build-signature-order"><img src="https://agentmods.dev/badge/skills/khaoss85/agent-crm/build-signature-order.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 | $0.00083 | $0.01755 |
| Opus 5 | $0.00042 | $0.00877 |
| Sonnet 5 | $0.00017 | $0.00351 |
| Haiku 4.5 | $0.00008 | $0.00176 |
Grade A, and why
build-signature-order 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orient yourself first
npm run crm -- app inspect --json
Read valid, then problems[], then limitations[], in that order. Every problem is fixed or reported before anything is built on top of it, and every limitation is a hard boundary on what you may claim. Then read packages[], capabilities[], resources[], actions[], policies[] and providers[]: that list is what exists. A capability absent from the report does not exist, whatever a record name, a label or a document suggests.
If the repository documents this skill names are absent, you are in a project built from this framework rather than in the framework itself. The inspection report is then the source of truth and those documents are optional background — do not guess at their contents, and do not assume a path exists because this skill names it.
providers[] reports declared metadata and the keys of a declared config, never a value. It is never evidence that a signature provider is credentialed, reachable or legally qualified — PROVIDER_HEALTH_UNKNOWN and SECRETS_NOT_INSPECTED are in limitations[] for exactly that reason.
Background, where they exist: ARCHITECTURE.md, DECISIONS.md (ADR-016 and ADR-017) and docs/SIGNATURE_ORDER.md. They are the deeper source for the rules below, not a prerequisite for them — the rules stand on their own.
Sequence an external side effect
- Never call a provider inside a database transaction, and never claim atomicity between the local database and a remote service. Declare the bounded external-operation shape instead:
externalOperation: 1withintent(transaction A),external(no transaction, bounded timeout),finalize(transaction B) andcompensate(its own transaction, only on failure). - The
externalphase gets frozen JSON-safe data plus the provider registry — no database, no modules, no managed writes. If you find yourself wanting a service handle there, the work belongs inintentorfinalize. - Give every external call a deterministic idempotency key derived from the record it belongs to (here:
env:quote-version:<id>, which is also the DB-unique source key). A repeated request must be refused, not retried into a second remote object. - On failure, move to a recoverable local state and record the phase and code. The single policy is: never silently retry, always reconcile.
- A provider answer that is already terminal is a completion, not a status: route every provider state through the one path that creates the artifact and the order, and prefetch what that needs in
external. Persisting a terminal state without its evidence is unrecoverable. - An idempotency key is a lookup, not an identity: before adopting a provider envelope, check the document hash, the signer set and any known provider envelope id, and fail closed on a mismatch.
- Do not build a scheduler, an outbox or a workflow DSL.
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 · 70 lines · 83 tokens per session scan A e2e6f1874887
build-signature-order is a skill published in the GitHub repository khaoss85/agent-crm (2 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,755 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
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
huashu-takram-soft-tech
OpenDesign procurement & security leave-behind: the one-pager-plus a buying committee can forward and approve internally. Built as a decision-grade B2B sales deck for buying committee, security, procurement.
dependency-audit
Audits direct and transitive dependencies for license compliance, maintenance health, CVEs, abandoned packages, and bloat. Triggers on: "audit dependencies", "license check", "dependency health", "abandoned packages", "unused dependencies", "license compliance", "supply chain", "dependency risk".
e-signature
Use when wiring an e-signature flow with DocuSign or Dropbox Sign — picking the SES/AES/QES legal tier, sending a PDF or template for signature, embedded signing, verifying signing webhooks, retrieving the signed PDF plus audit trail. NOT drafting contract text (that is contracts), NOT extracting fields from PDFs…
mcp-urgent-caller-triage
Prioritize inbound client calls by reading transcripts, classifying urgency, matching callers to legal client and matter context, and preparing a callback list for human review.
checking-legal-and-safety-wording
Reviews public text for license, warranty, compliance, safety, security, certification, and fitness claims that go too far, then rewrites them to stay inside the real limits. Use when shipping or editing public docs, READMEs, or rollout copy. Do not use for internal code comments, or for deciding actual legal fitness…