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 manishiitg/coding-agent-loop --skill support-case-to-reviewed-resolutiongit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/support-case-to-reviewed-resolution)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/support-case-to-reviewed-resolution"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/support-case-to-reviewed-resolution/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/manishiitg/coding-agent-loop/support-case-to-reviewed-resolution"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/support-case-to-reviewed-resolution.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 | $0.00027 | $0.00693 |
| Opus 5.5 | $0.00011 | $0.00277 |
| Sonnet 5.5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
support-case-to-reviewed-resolution 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 20d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Case to Reviewed Resolution
Outcome
Route one authorized customer case to an owned, sourced response or escalation. A drafted reply, approved reply, provider delivery, and observed resolution are separate states.
When to use
Use when a support team has a real case source, current approved help content, a contact owner, and a priority policy. Start with one manual case. Feedback theme analysis is a separate route.
Discovery and user direction
Inspect existing Support Crews, case and thread history, known incident state, help sources, prior contact, owners, and provider access. Propose reuse or reviewed creation. Show the exact case route before Builder applies it; selection leaves setup pending.
Required inputs
Bind tenant, case, account, recipient, channel, current thread revision, owner, priority rules, approved source revisions, and any escalation policy. Record who may approve contact and what source proves case closure.
Plan and AgentWorks tools
Reuse Support Triage Assistant and Support Reply Drafter; add Escalation Coordinator for a distinct receiving owner or boundary. Triage writes support-case-triage/v1; run the bundled validator before Reply or Escalation consumes it. Reply writes an unsent support-reply-draft/v1. Escalation writes support-escalation-brief/v1 with accepted owner state; validate it before Reply uses its claims. Insert explicit validator steps in the Workflow. Send only through a separately authorized action after exact approval and a fresh prior-contact check.
Knowledge and persistence
Save tenant, case, account, thread revision, source revisions, run, draft, approval, message fingerprint, delivery receipt, and outcome IDs. Re-read current case and thread before retries or scheduled runs; skip duplicate sends.
Validation and reporting
The validator checks joins, source evidence, draft state, escalation acceptance, delivery receipt, and observed closure. Fictional triage, reply, escalation, delivery, and outcome illustrate valid stages; the unsupported reply fails. The reporting dashboard shows queued, awaiting review, escalated, delivered, observed resolved, and blocked separately with source links and cost.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/approved-support-reply.json 792 B
- examples/case-outcome.json 346 B
- examples/invalid-support-reply-draft.json 456 B
- examples/provider-delivery.json 518 B
- examples/support-case-triage.json 619 B
- examples/support-escalation-brief.json 465 B
- examples/support-reply-draft.json 624 B
- playbook.json 5.0 KB
- references/team-and-handoffs.md 4.1 KB
- scripts/test_validate_handoff.py 3.8 KB runs code
- scripts/validate_handoff.py 7.3 KB runs code
- SETUP.json 3.1 KB
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.
- 20d ago First seen · 48 lines · 27 tokens per session scan A 923e99f4842f
support-case-to-reviewed-resolution is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 27 tokens to every session and 693 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
machinist
Use Machinist to create, assign, and monitor software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, intake labels, direct runs, or managed queue.
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
goga-task-by-specifying
Interactive task formulation from a raw request.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…