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 agentmods add skills/agent-engineer-master/skill-engineer/analyzing-feedbacknpx skills add Agent-Engineer-Master/skill-engineer --skill analyzing-feedbackgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWhat 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 | $0.00128 | $0.01141 |
| Opus 5 | $0.00064 | $0.00571 |
| Sonnet 5 | $0.00026 | $0.00228 |
| Haiku 4.5 | $0.00013 | $0.00114 |
Grade C, and why
analyzing-feedback scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer --> How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Feedback
Translates raw customer language into ranked, file-level structural edit proposals.
Reference files
references/feedback-taxonomy.md— categories, severity tiers, intent tags, negative triggersreferences/edit-proposal-template.md— A/B/C option output formatreferences/context-augmentation.md— codebase context packing guide
Process
Step 1 — Ingest and clarify
Receive raw feedback (pasted text, file path, or description). Check: is there at least one concrete user behaviour described (an action attempted, a screen visited, an outcome expected vs. received)?
If not — ask exactly one clarifying question: "What were users trying to do when they gave this feedback?"
If the feedback is multi-source (e.g. 50 reviews, a CSV), confirm the format before proceeding.
Do not scan the codebase until at least one concrete behaviour is confirmed.
Principle: the FeedbackEval benchmark shows raw human language feedback achieves only 50.5% edit success; converting to structured form first is the single highest-leverage step.
Step 2 — Categorize and cluster (human gate)
Read references/feedback-taxonomy.md. For each distinct piece of feedback, assign:
- Category — UX / Performance / Bug / Feature / Content / Other
- User intent — the underlying job-to-be-done (not the literal request)
- Severity — Critical / Important / Minor
- Pattern count — number of independent users/sources who mentioned this
Apply the pattern threshold: only advance themes with 2+ independent mentions OR Critical severity. Flag single-mention items explicitly — do not silently drop them.
Present the categorized table to the user:
Theme Category Severity Pattern count Advance?
→ Human gate: "Should I scan the codebase for these themes, or adjust any before I proceed?"
Do not continue to Step 3 until confirmed.
Step 3 — Scan codebase
What ships with it
5 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.
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 · 114 lines · 0 tokens per session scan C 37a07a3101e0
analyzing-feedback is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,141 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.