feedback-loop

feedback-loop is a skill for Claude Code, Codex from onixhdz/cartograph. It costs 15 tokens per session (2,074 once invoked), scanned A, original, MIT.

A repeatable process for improving cartograph’s analysis, ranking, and query algorithms through evaluation, diagnosis, fixes, re-indexing, and another evaluation. Re-indexing means processing the source repository again after a change.

In plain words
What is it for?
Reading acceptance criteria, running the specified evaluations, identifying remaining problems, changing the code, rebuilding, re-indexing, and checking the results again.
Why use it?
It turns an algorithm improvement into measurable pass-or-fail work based on an existing feedback plan instead of relying on guesswork.

Skill for Claude CodeCodex

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/onixhdz/cartograph/feedback-loop
Any agent
npx skills add onixhdz/cartograph --skill feedback-loop
Clone the repo
git clone --depth 1 https://github.com/onixhdz/cartograph

Made for: Claude Code, Codex.

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 feedback-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/onixhdz/cartograph/feedback-loop.svg)](https://agentmods.dev/skills/onixhdz/cartograph/feedback-loop)
Your own site
<a href="https://agentmods.dev/skills/onixhdz/cartograph/feedback-loop"><img src="https://agentmods.dev/badge/skills/onixhdz/cartograph/feedback-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,074 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 $0.00015 $0.02074
Opus 5 $0.00008 $0.01037
Sonnet 5 $0.00003 $0.00415
Haiku 4.5 $0.00002 $0.00207

Measured 3d ago against content hash e09dd356374c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-loop 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 3d 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.

.agents/skills/feedback-loop/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback Loop — Iterative Algorithm Improvement

Drive measurable improvements to cartograph's analysis, ranking, and query algorithms by executing an evaluate → diagnose → fix → re-index → re-evaluate cycle until every acceptance criterion in the feedback plan passes.

Prerequisites

  • A feedback plan file exists in plans/ (e.g., plans/cartograph-feedback-nomad-eval.md).
  • The target repository is already indexed or can be indexed with cartograph analyze.
  • The cartograph binary can be built with task build:dev from the workspace root.
  • cartograph is already on $PATH via dev symlink.

Workflow

Repeat the cycle below until all acceptance criteria in the plan pass or you are confident no further code changes can improve results.

Phase 0 — Read the Feedback Plan

  1. Read the feedback plan file end-to-end. Identify:
    • Acceptance criteria — the numbered pass/fail conditions at the top.
    • Reproduction commands — the exact cartograph invocations to run.
    • Remaining issues — the narrative descriptions of what is still broken.
    • Scores — the per-capability scores and overall target.
  2. Build a todo list from the acceptance criteria so progress is trackable.

Phase 1 — Build & Start Service

  1. Kill the running binary and stop the background service before building to ensure the old binary is not held by a running process and the new binary is picked up cleanly:
    pkill -f cartograph 2>/dev/null || true
    cartograph serve stop 2>/dev/null || true
    
    This is a no-op if no process or service is running.
  2. Run cd /workspaces/cartograph && task build:dev to compile the updated binary.
  3. If the build fails, fix compilation errors before proceeding.
  4. Start the background service so queries can be dispatched in parallel:
    cartograph serve start
    
    Wait briefly for the service to be ready before proceeding to evaluation.

Phase 2 — Evaluate

  1. Run every reproduction command from the plan exactly as written.
    • With the service running, dispatch independent queries in parallel to speed up evaluation. Group queries that don't depend on each other and launch them concurrently.
    • Capture output for each command.
    • For cypher queries, pipe through head -40 to keep output manageable.
  2. For each acceptance criterion, record pass or fail with a one-line evidence note.
  3. If all criteria pass, stop — report success and the final scores.

Read the full file on GitHub · 142 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. 3d ago First seen · 142 lines · 15 tokens per session scan A e09dd356374c

Subscribe to this mod's changes

feedback-loop is a skill published in the GitHub repository onixhdz/cartograph (11 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 2,074 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens