Claude-Mind: Skill for Claude Code

.claude/skills/felt-sense-checkin/SKILL.md

felt-sense-checkin is a skill for Claude Code from zkysar1/Claude-Mind. It costs 238 tokens per session (16,452 once invoked), scanned A, original, MIT.

A structured self-review that runs after every 75 completed goals, or when requested, to examine an agent's memory, safeguards, work history, and current difficulties.

In plain words
What is it for?
Use it to review recent goal cycles, update stored insights and safeguards, identify new goals, and surface what is causing friction.
Why use it?
It helps detect outdated records, missed follow-up work, recurring problems, and changes the agent should make to its process.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is zkysar1/Claude-Mind's own configuration. It tells Claude Code how to work on Claude-Mind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Mind configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash: bash core/scripts/world-cat.sh conventions/capability-routing.md.

Reuse

Borrowing it

Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/felt-sense-checkin/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zkysar1/Claude-Mind

Made for: Claude Code.

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 felt-sense-checkin

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkysar1/claude-mind/felt-sense-checkin/github.svg)](https://agentmods.dev/skills/zkysar1/claude-mind/felt-sense-checkin)
Your own site
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/felt-sense-checkin"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/felt-sense-checkin/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 felt-sense-checkin

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/felt-sense-checkin"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/felt-sense-checkin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 238 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,452 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 $0.00238 $0.16452
Opus 5 $0.00119 $0.08226
Sonnet 5 $0.00048 $0.03290
Haiku 4.5 $0.00024 $0.01645

Measured 8d ago against content hash 956b1d12f983, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

felt-sense-checkin 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.

.claude/skills/felt-sense-checkin/SKILL.md · 1,070 lines

How it starts

The opening of the file, as written. The whole thing — 1,070 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/felt-sense-checkin — Structured 7-Lane Self-Audit

Every 75 completed goals (or on user demand), run the seven-lane sweep that converts the user's 2026-04-22 diagnostic question into an autonomous routine:

"Think about updates to tree / journal / guardrails / experiences from this cycle. Out-of-cycle completions? Unblocks? New goals or aspirations? Anything to add to /verify-learning? Do you need to change your meta? And — how are you feeling? Where is the pain? What would you change?"

That one question produced more actionable diagnosis in one turn than a week of autonomous operation. This skill makes the agent ask it autonomously, with structured output and direct writes.

Cadence Gate

IF args contains "--cadence":
    # Auto-invocation from aspirations-precheck Phase 0.5f — honor the gate.
    Bash: core/scripts/felt-sense-cadence-check.sh --verbose
    IF exit 1 (noop): STOP — cadence not crossed.
    IF exit 0 (fire): continue.
ELSE:
    # Bare user invocation (/felt-sense-checkin with no args) — the user
    # asked explicitly, so skip the cadence check and run the sweep now.
    continue.

Phase 1: Memory Hygiene Sweep

Look at the last ~75 completed goals (or since last_felt_sense_checkin). For each mistake, near-miss, or lesson surfaced during that window:

  • Tree: Is there a knowledge gap that should become a tree node? If yes, /tree add with the lesson. Don't defer to "next consolidation."
  • Reasoning bank: Did an ABC chain repeat? reasoning-bank-add.sh.
  • Guardrails: Did a mistake recur that needs a trigger-condition rule? guardrails-add.sh.
  • Experience: Did a particularly rich trace not get archived? experience-add.sh.

Write each. Report count per store in the final summary.

Phase 1b: Insight Curation (closes the /prime surface from Part B)

capture-insights.py writes to agents/<agent>/insights.jsonl during sparks and execution reflections. /prime Phase 4 surfaces the top 5 unprocessed entries with a curation-debt suffix at ≥50. This step is the curation side of that pipeline: the felt-sense sweep reads the backlog, distills the keepers into the durable stores (tree / reasoning bank / guardrails / experience), and marks the queue processed so the /prime surface recovers a clean baseline.

Read the full file on GitHub · 1,070 lines

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. 8d ago Changed · +27 lines 956b1d12f983
  2. 12d ago First seen · 1,043 lines · 238 tokens per session scan A a434671f5ff3

Subscribe to this mod's changes

felt-sense-checkin is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 238 tokens to every session and 16,452 once invoked, about $0.0012 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.