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/indranilbanerjee/socialforgeWrote 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/indranilbanerjee/socialforge/check-approvals)<a href="https://agentmods.dev/commands/indranilbanerjee/socialforge/check-approvals"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/socialforge/check-approvals/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/indranilbanerjee/socialforge/check-approvals"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/socialforge/check-approvals.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 | $0.00009 | $0.00136 |
| Opus 5 | $0.00005 | $0.00068 |
| Sonnet 5 | $0.00002 | $0.00027 |
| Haiku 4.5 | $0.00001 | $0.00014 |
Grade A, and why
check-approvals 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 9d 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
Check Approvals
Show all pending approvals and optionally send overdue reminders.
Output
Pending Approvals — AcmeCorp / April 2026
Internal review: 3 posts (P14, P18, P22) — 2 days pending
Client review: 5 posts (P01-P05) — sent 3 days ago, reminder due
CEO approval: 1 post (P01 HERO) — waiting
--send-reminders to notify overdue reviewers
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.
- 9d ago First seen · 19 lines · 9 tokens per session scan A a5558f25b8ab
check-approvals is a command published in the GitHub repository indranilbanerjee/socialforge (37 stars, last pushed 23d ago), licensed MIT. It adds 9 tokens to every session and 136 once invoked, about $0.0000 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
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
status
Reports where the project stands in the RENATA flow and points to the next step, gating the current step behind human verification, without running any step commands.
triage
Triages an unprioritized list of bugs, debt, and tasks into a full MoSCoW breakdown with justification and an attack order.
prd
Generates or refines a one-page Micro PRD for a product or feature in the RENATA standard.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
lead
Tech lead: classify, quiz, ticket on the owning repo, dispatch. Do not implement.