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.
npx skills add indranilbanerjee/neels-plugins --skill manage-reviewsgit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/manage-reviews)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/manage-reviews"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/manage-reviews/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/indranilbanerjee/neels-plugins/manage-reviews"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/manage-reviews.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 | $0.00025 | $0.00464 |
| Opus 5.5 | $0.00010 | $0.00186 |
| Sonnet 5.5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
manage-reviews 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 2d 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.
This is a copy
94% identical to manage-reviews — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/socialforge:manage-reviews — Review & Approval Manager
Manage the multi-tier approval workflow per brand's approval-chain.json.
Approval Tiers
- HERO content: Internal review → Client approval → CEO approval (if configured)
- HUB content: Internal review → Client approval (optional)
- HYGIENE content: Internal review only (auto-approvable if configured)
Actions
/socialforge:manage-reviews --approve P04— Approve post P04 at current tier/socialforge:manage-reviews --revise P04 "Make the background warmer"— Request revision with feedback/socialforge:manage-reviews --client-send— Send all internally-approved posts to client review/socialforge:manage-reviews --check— Check pending approvals and send reminders
State Transitions
QUEUED → ASSET_MATCHING → GENERATING → PENDING_REVIEW PENDING_REVIEW → APPROVED_INTERNAL | REVISION_REQUESTED | REJECTED REVISION_REQUESTED → GENERATING (re-enters production with feedback) REJECTED → QUEUED (start over) APPROVED_INTERNAL → PENDING_CLIENT (if client review required) | FINAL (if not) PENDING_CLIENT → APPROVED_CLIENT | REVISION_REQ_CLIENT | REJECTED_CLIENT APPROVED_CLIENT → PENDING_CEO (if CEO required) | FINAL (if not) PENDING_CEO → APPROVED_CEO → FINAL FINAL → (write-protected, no transitions)
Rules
- FINAL status is write-protected — cannot be modified after finalization
- Revision requests re-enter the generation pipeline with specific feedback
- Max 3 revision cycles per HERO post before escalation
- Reminders sent via Slack/email after N days (per escalation_rules)
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.
- 2d ago First seen · 41 lines · 25 tokens per session scan A 1d2ca7fce70a
manage-reviews is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 464 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to manage-reviews, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
import-sop
Import agency procedures as role-assigned SOP steps with approval gates. "import our launch checklist".
webinar-plan
Plan a webinar end to end: run of show, registration copy, promotion, follow-up. "plan a webinar on X".
client-onboarding
Build a client onboarding pack: kickoff agenda, discovery questions, 30-60-90. "we just signed a new client".
marketing-project-mgmt
Marketing project management and execution excellence for B2B SaaS campaigns. Use this skill when coordinating multi-channel campaigns, allocating team resources, planning agile marketing sprints, running QBRs with clients, managing project timelines, balancing marketing workload, or implementing marketing operations…
hoo-task-board
Use to view or mirror the work queue - "task board", "show the queue", /organic-os:task-board. Mirrors to Notion when that connector exists; local queue.md is the source of truth.