agentmods.dev

log-feedback

log-feedback is a skill for Claude Code from tomthebearded/guide-forge. It costs 140 tokens per session (601 once invoked), scanned A, original, MIT.

A guide-maintenance skill that records reader problems in a dated feedback log without changing the guide itself.

In plain words
What is it for?
Use it to document where a reader got stuck, what happened, likely problem type, severity, tags, and their words.
Why use it?
It preserves reports of confusing or difficult steps so they can be reviewed and fixed later.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

Part of the guide-forge plugin — 15 skills shipped together

not rated 3repo 1mo ago A scan 140 tokens original MIT

Good fit Use it to document where a reader got stuck, what happened, likely problem type, severity, tags, and their words.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomthebearded/guide-forge/log-feedback
View source ↗ tomthebearded/guide-forge
Install

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.

Any agent
npx skills add tomthebearded/guide-forge --skill log-feedback
Clone the repo
git clone --depth 1 https://github.com/tomthebearded/guide-forge

Made for: Claude Code.

Or install guide-forge, the plugin that ships this one along with the rest of its 15 skills.

Wrote 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.

agentmods badge for log-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomthebearded/guide-forge/log-feedback/github.svg)](https://agentmods.dev/skills/tomthebearded/guide-forge/log-feedback)
Your own site
<a href="https://agentmods.dev/skills/tomthebearded/guide-forge/log-feedback"><img src="https://agentmods.dev/badge/skills/tomthebearded/guide-forge/log-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.

agentmods 80×15 button for log-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomthebearded/guide-forge/log-feedback"><img src="https://agentmods.dev/badge/skills/tomthebearded/guide-forge/log-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 601 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.00601
Opus 5.5 $0.00056 $0.00240
Sonnet 5.5 $0.00028 $0.00120
Haiku 4.5 $0.00014 $0.00060

Measured 2mo ago against content hash e85b74ca6dac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

log-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.

skills/log-feedback/SKILL.md · 43 lines

What it actually says

Skill: log-feedback

The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:

!cat "${CLAUDE_SKILL_DIR}/prompt.md"

(If the block above came back empty or errored, read prompt.md in this skill folder — it sits beside this SKILL.md — and follow that.)

As you follow it, adapt for the fact that you're a Claude Code skill, not a pasted prompt:

  • You're already invoked — skip its "How to use / paste this" preamble. The field report(s) are $ARGUMENTS below (plus any attached files — an error log, a screenshot description, the file the reader was working in). Read the guide's guide/ files yourself to place the report.
  • You have file tools here — append the entry to guide/feedback-log.md on disk, rather than only printing a fenced block. Create the ledger from templates/feedback-log.md if it's missing.
  • Log-only — touch nothing else. Do not edit step files, status.md, decision-log.md, or the guide README.md. The only file this skill writes is guide/feedback-log.md.
  • Locate to log, not to fix. Search the guide to fill Where accurately; do not edit the step you find.
  • When a real fix is warranted, hand off to the sibling skill /report-issue — say so; don't fix here.

Field report(s) / args:

$ARGUMENTS

Gate: this skill captures, it does not repair — append to guide/feedback-log.md and change nothing else; one entry per distinct piece of friction, faithful to what the reader experienced, guesses labelled as guesses; point the user to /report-issue if the guide should actually be fixed. Leave the entry in the working tree — do not commit.

Files

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.

Changes

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.

  1. 2mo ago First seen · 43 lines · 140 tokens per session scan A e85b74ca6dac

Subscribe to this mod's changes

log-feedback is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 601 once invoked, about $0.0006 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.

Claude CodeLearning and teachingclaude-code-plugindeveloper-educationtechnical-writing
Related

log-feedback compared with skills from other repositories

log-feedback next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
log-feedbacktomthebearded/guide-forgeSkill31mo agoMITA140Claude Code
learning-tutorpsreek-ai/codebase-moocSkill17mo agononeA111Claude Code
curriculum-reviewerpsreek-ai/codebase-moocSkill17mo agononeA82Claude Code
learning-and-developmentcbrock84/headcountSkill2.6k25d agoMITA64Claude Code
onboarding-expressmagic5644/Graph-It-LiveSkill63todayMITA171Claude Code
eli5thoughtbot/rails-consultantSkill296d agoMITA13Claude Code
teach-medoodledood/manifest-devSkill783d agoMITA121Claude Code