feedback-analysis

A review method for comparing predictions with what actually happened months later. Repeated reviews reveal which judgments are reliable and where blind spots exist.

In plain words
What is it for?
Use it to record expectations, assumptions, success criteria, and later results for important decisions or actions.
Why use it?
It replaces vague self-assessment with evidence from past decisions and outcomes.

Skill for Claude CodeCodex

Part of the instinct plugin — 54 skills, 1 hook shipped together

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.

agentmods
npx agentmods add skills/tupe12334/instinct/feedback-analysis
Any agent
npx skills add tupe12334/instinct --skill feedback-analysis
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

Made for: Claude Code, Codex.

Or install instinct, the plugin that ships this one along with the rest of its 54 skills, 1 hook.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.01838
Opus 5 $0.00009 $0.00919
Sonnet 5 $0.00004 $0.00368
Haiku 4.5 $0.00002 $0.00184

Measured 2d ago against content hash 8579e582cbd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-analysis 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 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.

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/feedback-analysis/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback Analysis

Overview

Method developed by Peter Drucker. Before taking action or making a decision, write down what you expect to happen. Then, 9–12 months later, compare actual results to expectations. Repeated over time, this surfaces your actual strengths, weaknesses, and blind spots — not your assumed ones.

Core insight: most people don't know what they're actually good at. Systematic feedback analysis reveals it objectively.

How to Apply

Step 1 — Record expectations (before action)

Whenever you make a significant decision or take a key action, write:

  • Date: [today]
  • Decision/Action: [what you're doing]
  • Expected outcome: [what you predict will happen, and by when]
  • Key assumptions: [what must be true for your prediction to hold]
  • Success criteria: [how you'll know the outcome was what you expected]

Store this somewhere reviewable (notes app, journal, database).

Step 2 — Review (9–12 months later)

Retrieve your original record and compare:

  • Actual outcome: [what happened]
  • Prediction accuracy: [on track / better than expected / worse than expected]
  • Variance explanation: [why did reality differ from prediction?]

Step 3 — Pattern analysis (after multiple cycles)

After 6+ feedback cycles, look for patterns:

Identify strengths: Areas where your predictions consistently match or beat reality. These are your actual competencies — lean into them.

Identify weaknesses: Areas where results consistently disappoint expectations. Either improve these skills or stop relying on them.

Identify blind spots: Areas where you were confidently wrong. These require the most attention — wrong confidence is more dangerous than acknowledged uncertainty.

Identify waste: Tasks or areas where you invest significant time but results are mediocre. Consider stopping or delegating.

Step 4 — Act on findings

  • Double down on strengths: Allocate more time and resources here; this is where you create the most value
  • Remediate critical weaknesses: If a weakness blocks your goals, address it; otherwise, work around it
  • Fix or avoid blind spots: Either acquire feedback sooner next time, or stop operating in areas where your judgment is systematically unreliable
  • Eliminate wasted effort: Stop doing things you're not good at and don't need to be good at

Read the full file on GitHub · 139 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. 2d ago First seen · 139 lines · 18 tokens per session scan A 8579e582cbd3

Subscribe to this mod's changes

feedback-analysis is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 18 tokens to every session and 1,838 once invoked, about $0.0001 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.