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 agentmods add skills/dr-code/tessera/systematic-debuggingnpx skills add dr-code/tessera --skill systematic-debugginggit clone --depth 1 https://github.com/dr-code/tesseraWhat 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 | $0.00021 | $0.00968 |
| Opus 5 | $0.00010 | $0.00484 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
systematic-debugging 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 yesterday.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Overview
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
Tessera: Map Blast Radius First
Before starting Phase 1 — if tessera MCP is configured in this session:
1. graph_continue (mandatory first call)
2. graph_impact(changed_files=["<file where bug was reported>"])
graph_impact shows which other files depend on the broken code. This tells you:
- How far a fix might ripple
- Which tests are likely affected
- Whether this is a leaf-level bug or a core abstraction issue
Surface this impact map before investigating root cause.
The Four Phases
You MUST complete each phase before proceeding to the next.
Phase 1: Root Cause Investigation
BEFORE attempting ANY fix:
- Read error messages carefully — stack traces, line numbers, error codes
- Reproduce consistently — can you trigger it reliably every time?
- Check recent changes — git diff, recent commits, new dependencies
- Gather evidence in multi-component systems
- Add diagnostic logging at each component boundary
- Run once to gather evidence showing WHERE it breaks
- Then analyze to identify the failing component
- Trace data flow — where does the bad value originate? Trace backward through the call stack
Phase 2: Pattern Analysis
- Find working examples — use
graph_retrieve(query="<working component similar to broken one>")if tessera MCP is configured to find similar code in the codebase - Read the reference — use
graph_readto read the working implementation completely, not just skim - Identify differences — list every difference, however small
- Understand dependencies — what settings, config, environment does this need?
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.
- yesterday First seen · 112 lines · 21 tokens per session scan A 645865319a9b
systematic-debugging is a skill published in the GitHub repository dr-code/tessera (1 stars, last pushed 21d ago), licensed MIT. It adds 21 tokens to every session and 968 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…