Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/run-queue)<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/run-queue"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/run-queue.svg" alt="Measured on agentmods" 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 | $0.04875 |
| Opus 5 | $0.00000 | $0.02438 |
| Sonnet 5 | $0.00000 | $0.00975 |
| Haiku 4.5 | $0.00000 | $0.00487 |
Grade A, and why
run-queue 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 3d 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run-queue — Autonomous Skill Queue Runner
Runs the next task from MASTER_QUEUE.md end-to-end with no human input.
Reads the queue, finds the first incomplete task, executes it fully, marks it done, commits, and exits.
The next invocation picks up the next task automatically.
Step 0 — Configure git push (run once at session start)
The CCR environment proxies git through a local service that may block pushes. Before doing any work, reconfigure the remote to use the authenticated HTTPS URL:
git remote set-url origin https://github.com/PranavNagrecha/AwesomeSalesforceSkills.git
git config user.email "[email protected]"
git config user.name "SfSkills Agent"
Then verify push works:
git push origin main --dry-run 2>&1
If the dry-run fails with 403, the environment does not have write credentials.
In that case: commit locally, then use the GitHub MCP push_files tool to upload
only the text files that changed (skip binary files: *.sqlite, *.pyc, __pycache__/).
The chunks.jsonl and lexical.sqlite in vector_index/ will be regenerated on the
next run via python3 scripts/skill_sync.py --all — do not attempt to push them via MCP.
Note: lexical.sqlite is listed in .gitignore (file size grows past GitHub's 50 MB limit).
If the local index is missing or stale, regenerate it before running any search:
python3 scripts/skill_sync.py --all
Step 1 — Read the Queue
cat MASTER_QUEUE.md
Find the first row where Status is TODO or RESEARCH.
Read the entire row: Status, Skill Name (or Research Task), Description, Cloud, Role, Domain.
If no TODO or RESEARCH rows exist → the queue is complete. Print "QUEUE COMPLETE" and stop.
Step 2 — Branch on Task Type
If the task is RESEARCH
Goal: populate the empty skill rows for a Cloud × Role cell.
2a. Mark in-progress
Edit MASTER_QUEUE.md: change RESEARCH → IN_PROGRESS on that row. Add timestamp.
2b. Web search — ground everything in official docs
Search for: "Salesforce <Cloud> <Role> tasks site:help.salesforce.com OR site:developer.salesforce.com OR site:trailhead.salesforce.com"
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.
- 3d ago First seen · 481 lines · 0 tokens per session scan A 9bf66a04cfe3
run-queue 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 4,875 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 2026-09-03.
Other commands, from other repositories
gsd:quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
company-repo
Gestionar el repositorio Company Savia: crear, conectar, estado, sincronizar. El repositorio compartido de la empresa para conocimiento, mensajería y estado.
contribute
Contribuir mejoras, ideas o correcciones al repositorio de pm-workspace en GitHub.
backlog-sync
Sync local backlog with external PM tools (Azure DevOps, Jira, GitHub Issues).
gsd:pause-work
Create context handoff when pausing work mid-phase.
gsd:remove-phase
Remove a future phase from roadmap and renumber subsequent phases.