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 bestdeejay-design/agent-skills --skill skill-feedbackgit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/bestdeejay-design/agent-skills/skill-feedback)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/skill-feedback"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/skill-feedback.svg" alt="Measured on agentmods" 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 | $0.00195 | $0.01696 |
| Opus 5 | $0.00097 | $0.00848 |
| Sonnet 5 | $0.00039 | $0.00339 |
| Haiku 4.5 | $0.00019 | $0.00170 |
Grade A, and why
skill-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 8d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Feedback — capture the fuel for skill improvement
This skill closes the loop opened by docs/SKILL_QUALITY_GATE.md. The Quality
Gate tells you whether a skill is good; this skill tells you how to make it
better next time by recording what happened in real usage and turning it into
a feed for skill-forge.
Without a feedback capture, improvement is guesswork. With it, every near-miss
trigger and every manual correction becomes a concrete edit to a skill's
description / when_to_use / body.
When to use
- A skill should have triggered but did not (near-miss): the user's request was in-scope but the auto-load missed it.
- A skill triggered wrongly: the wrong skill loaded for the request.
- A skill produced a wrong / broken / low-quality output (output issue).
- The user manually corrected the skill's output (edited the result, or told you "no, do it differently").
- You want to review what has piled up before running
skill-forge.
DO NOT USE FOR
- General chat feedback, venting, or notes unrelated to a specific skill — those belong in memory or the session log, not the skill feedback store.
- Capturing secrets or personal data — never log credentials or PII in entries.
Auto-capture (make it automatic)
For the loop to run without manual nudging, capture feedback proactively.
Append the rule from AGENTS_FRAGMENT.md (repo root) to your opencode
AGENTS.md. Then any near-miss / manual correction is logged automatically —
no explicit "remember this" needed. Each consumer grows their own skills
locally; see docs/SKILL_QUALITY_GATE.md Layer C.
How feedback is stored
Each entry is one JSON object on its own line in:
feedback/<skill-name>/YYYY-MM-DD.jsonl
Entry schema:
{
"ts": "2026-08-26T14:03:00",
"skill": "api-contract-testing",
"type": "near_miss_trigger",
"request": "проверь, что эндпоинты совпадают со спецификацией",
"detail": "skill did not auto-load; user had to invoke it manually",
"suggested_fix": "add casual-phrasing trigger 'проверь эндпоинты' to when_to_use",
"source": "user"
}
What ships with it
2 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.
- 8d ago First seen · 132 lines · 195 tokens per session scan A d2c847395f37
skill-feedback is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed today), licensed MIT. It adds 195 tokens to every session and 1,696 once invoked, about $0.0010 per session on Opus 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.
Other skills, from other repositories
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).
context-compactor
9-section context compression with analysis scratchpad. Adapted from Claude Code's /compact system (2026-03-31).
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).
trade-journal-analyzer
Unified post-trade analytics: journal pattern extraction + drawdown classification. Absorbs: drawdown-classifier.
Deep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.