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 Rabithua/FeedbackServerPlugin --skill triage-feedbackgit clone --depth 1 https://github.com/Rabithua/FeedbackServerPluginWrote 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/rabithua/feedbackserverplugin/triage-feedback)<a href="https://agentmods.dev/skills/rabithua/feedbackserverplugin/triage-feedback"><img src="https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/triage-feedback/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/rabithua/feedbackserverplugin/triage-feedback"><img src="https://agentmods.dev/badge/skills/rabithua/feedbackserverplugin/triage-feedback.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 | $0.00063 | $0.00473 |
| Opus 5.5 | $0.00025 | $0.00189 |
| Sonnet 5.5 | $0.00013 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
triage-feedback 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 2mo 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
Triage FeedbackServer 2.0 feedback
Verify the connected account with whoami when needed. Resolve the Product with list_products and
the record with list_feedback or get_feedback; auto-select only one unambiguous result. Otherwise
ask. Pass explicit Product and entity IDs to later tools and follow nextCursor until the requested
range is complete.
Keep internal notes, client context, visitor credentials, waitlist data, and diagnostics private.
Call get_attachment_url only when the task requires an attachment, and call
get_diagnostic_bundle_url only for an explicit diagnostic inspection or download request.
An explicit request to change a specific Feedback record's status or visibility authorizes the exact
update_feedback call. An explicit request to send specified reply text authorizes the exact
reply_to_feedback call. Execute either ordinary write once without asking the user to approve the
same action again. Explicit requests for an internal note or Item link similarly authorize the
matching direct tool. Drafting, reviewing, planning, previewing, or summarizing does not authorize a
write. Public Feedback exposes its body, attachments, author display code, and non-internal thread as
one unit; diagnostics and internal notes remain private.
Deletion and any other tool marked risky prefer native MCP elicitation. If elicitation is unavailable
and a call returns confirmation_required, show the exact Product, entity, visible or destructive
effect, and full public text when relevant. After explicit approval, repeat the same tool with
identical arguments plus confirm: true. Never use a confirmation identifier or alter the approved
payload. If state changed, reread it and seek fresh approval; never retry a write automatically.
Preserve error status, code, message, request ID, retry guidance, and remediation. On 401 route to
$setup-feedback-server; on 403 report the missing scope or access and stop. Never ask for a token.
What ships with it
1 file 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.
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.
- 2mo ago Changed · +4 lines · +3 tokens per session 6205fa67f727
- 2mo ago First seen · 29 lines · 60 tokens per session scan A 8834c8060408
triage-feedback is a skill published in the GitHub repository Rabithua/FeedbackServerPlugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 473 once invoked, about $0.0003 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 2026-08-31.
triage-feedback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triage-feedbackRabithua/FeedbackServerPlugin | Skill | 0 | 2mo ago | MIT | A | 63 | Claude Code, Codex |
| trulens-evaluation-setuptruera/trulens | Skill | 3.7k | 2d ago | MIT | A | 17 | Claude Code, Codex |
| honesty-communicationkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 151 | Claude Code, Codex |
| agent-self-evalcoco-research/coco | Skill | 632 | yesterday | Apache-2.0 | A | 46 | Claude Code, Codex |
| code-review-qualityproffesor-for-testing/agentic-qe | Skill | 529 | yesterday | MIT | A | 33 | Claude Code |
| self-improverAffitor/affiliate-skills | Skill | 786 | 27d ago | MIT | A | 87 | Claude Code |
| Effective Memoryplur-ai/plur | Skill | 317 | yesterday | Apache-2.0 | A | 43 | Claude Code |