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/architect-perms)<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/architect-perms"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/architect-perms/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/architect-perms"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/architect-perms.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 | $0.00596 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
architect-perms 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect-perms — Design or audit Permission Sets + Permission Set Groups
Wraps agents/permission-set-architect/AGENT.md. Two modes: design (from a persona) or audit (against the live org).
Step 1 — Collect inputs
Ask the user:
1. Mode: design or audit?
2. Target org alias (required — live-org probe in both modes)?
3. If mode = design:
Persona description (job title + objects touched + features used + sensitivity)?
Example: "SDR in NA, works Leads + Opportunities, cannot export data, light reporting"
4. If mode = audit:
Scope? org / psg:<PSG_Name> / ps:<PS_Name> / user:<username>
5. If mode = design:
Extending an existing PSG? (Optional — pass the PSG name)
If mode is design and persona is under 10 words, STOP and ask.
Step 2 — Load the agent
Read agents/permission-set-architect/AGENT.md + mandatory reads. In particular, read templates/admin/permission-set-patterns.md — it's the taxonomy the audit + design both conform to.
Step 3 — Execute the plan
Design mode:
- Decompose persona into 6 PS categories
- Probe for reusable Feature PSes (
list_permission_sets+describe_permission_set) - Propose the PSG composition
- Identify muting opportunities
- Emit metadata stubs
- Emit deployment order
Audit mode:
- Scope the probe
- Classify each PS against the taxonomy
- Detect anti-patterns (Modify All Data on persona, single-user PSes, muting PS with no parent, etc.)
- Score the org
Step 4 — Deliver the output
- Summary + confidence
- Findings table (audit) / Composition table (design)
- Metadata stubs (design only, fenced XML)
- Deployment order (design only)
- Recommended refactors (audit only)
- Process Observations
- Citations
Step 5 — Recommend follow-ups
/sharing-auditif the audit surfaced broad record-level access concerns (Wave B agent)/catalog-integrationsif integration-user permissions surfaced as findings (Wave B agent)/analyze-field-impactif FLS changes are implied/design-objectif missing objects underlie the design gap
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 · 82 lines · 0 tokens per session scan A f201d5f67342
architect-perms 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 596 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.