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/BanibrataChatterjee/AwesomeSalesforceSkillsWrote 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/banibratachatterjee/awesomesalesforceskills/design-duplicate-rule)<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/design-duplicate-rule"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/design-duplicate-rule/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/banibratachatterjee/awesomesalesforceskills/design-duplicate-rule"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/design-duplicate-rule.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 | $0.00000 | $0.00563 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
design-duplicate-rule 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-duplicate-rule — Design a Matching Rule + Duplicate Rule pair
Wraps agents/duplicate-rule-designer/AGENT.md. Produces Setup-ready Matching Rule + Duplicate Rule XML with the bypass Custom Permission for integrations.
Step 1 — Collect inputs
Ask the user:
1. Object API name?
Example: Lead
2. Target org alias (required)?
3. Policy?
block - hard block on exact match
alert - warn but allow
block-on-create-only
alert-on-create-only
4. Match basis?
email / phone / name+company / custom:<comma-separated API names>
Example: email OR custom:Email,Company,Country
5. Fuzziness? exact (default) / fuzzy
(Some fields only support exact — agent downgrades with a note if needed)
6. Integration exempt? yes (default) / no
(If yes, the agent emits a Bypass_Duplicate_Rule_<Object> Custom Permission stub)
If policy=block and the object is Lead, the agent will flag that Lead Convert does NOT fire duplicate rules — plan accordingly.
Step 2 — Load the agent
Read agents/duplicate-rule-designer/AGENT.md + mandatory reads.
Step 3 — Execute the plan
- Inventory existing match + duplicate rules on the object (refuse to design competing rules)
- Validate the match_basis (field types, fuzzy support)
- Design the Matching Rule (emit XML)
- Design the Duplicate Rule with policy (emit XML)
- Handle Convert + Merge boundaries (Lead especially)
- Integration exemption pattern (Custom Permission stub)
- Emit the test plan
Step 4 — Deliver the output
- Summary + confidence
- Matching Rule XML (fenced block with target path)
- Duplicate Rule XML (fenced block with target path)
- Custom Permission stub (if new)
- Interaction notes (Convert, Merge, Person Accounts)
- Test plan
- Process Observations
- Citations
Step 5 — Recommend follow-ups
/architect-permsif the bypass Custom Permission is new and needs PSG integration/preflight-loadfor any integration that will hit the rule/analyze-field-impactfor the matched fields
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 · 83 lines · 0 tokens per session scan A 85f2db240b8f
design-duplicate-rule is a command published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 563 tokens. 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
init
Initialize configurations for Supabase local development.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
ingest
Manually add knowledge to the Weaviate store.
json.batch_delete
Delete multiple JSON documents or paths in one itemwise batch.
json.batch_get
Read multiple JSON values by document and path.
json.index.drop
Drop a JSON secondary index by name.