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 verified-knowledge-to-case-replygit 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/verified-knowledge-to-case-reply)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/verified-knowledge-to-case-reply"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/verified-knowledge-to-case-reply/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/verified-knowledge-to-case-reply"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/verified-knowledge-to-case-reply.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 | $0.00029 | $0.00582 |
| Opus 5.5 | $0.00012 | $0.00233 |
| Sonnet 5.5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
verified-knowledge-to-case-reply 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 19d 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.
Verified Knowledge to Case Reply
Outcome
Produce a verified live knowledge reference and an exact-case reply draft with source links and a contact decision.
When to use
Use this route when the job crosses the listed owners or access boundaries. A single Crew may do a compatible read-only task. This package is a Builder proposal, not an active automation.
Discovery and user direction
Inspect existing Crews, source access, policy revisions, owner decisions and the exact subject. Ask only for missing facts, then show the proposed route for review.
Required inputs
One product, help article and exact open case, locale, recipient, support owner and contact policy. Read the live help revision and publication receipt, current case thread and account state, approved product facts and suppression history.
Plan and AgentWorks tools
Create reviewed steps for support-knowledge-curator (support-knowledge-publication/v1) → support-reply-drafter (support-reply-draft/v1). Reuse Crews where compatible; Builder may propose create_crew for a missing role. Validate each typed artifact before the next step and independently re-read current source state. No article publication, case closure, customer send or deflection claim from selecting this Playbook or drafting a reply.
Knowledge and persistence
Store tenant, subject, Crew, artifact, source revision, decision, approval and provider receipt IDs. Re-read source truth and deduplicate on repeat; keep prior decisions in the ledger.
Validation and reporting
The contract validator checks exact identity, revisions, time order and route-specific false claims. The first artifact, last artifact and rejected artifact exercise it. The dashboard must separate pending review, owner approval and observed provider action.
Guardrails
An approved article draft is not live knowledge. Recheck the published revision, case applicability and permission before a separate reply approval. No article publication, case closure, customer send or deflection claim from selecting this Playbook or drafting a reply. Do not count a draft, approval or planned action as a provider outcome.
What ships with it
9 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/invalid-reply.json 848 B
- examples/knowledge.json 723 B
- examples/reply.json 850 B
- playbook.json 5.0 KB
- references/team-and-handoffs.md 1.7 KB
- scripts/additional_route_contract.py 8.8 KB runs code
- scripts/test_validate_handoff.py 1.2 KB runs code
- scripts/validate_handoff.py 649 B 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.
- 19d ago First seen · 48 lines · 29 tokens per session scan A bdeb4565c01a
verified-knowledge-to-case-reply is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 582 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 2026-09-28.
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.
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.
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…
goga-specify
User task formulation specialist.
design-debt-tracker
Use when critique or review produces deferred findings, when checking accumulated design compromises, or when deciding what to address in the next iteration. Maintains a living register of design debt — the minor issues, future-iteration notes, and conscious compromises that accumulate across a project.