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 skills add abstractonion/cadence --skill investigate-before-fixinggit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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.
[](https://agentmods.dev/skills/abstractonion/cadence/investigate-before-fixing)<a href="https://agentmods.dev/skills/abstractonion/cadence/investigate-before-fixing"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/investigate-before-fixing/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.
<a href="https://agentmods.dev/skills/abstractonion/cadence/investigate-before-fixing"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/investigate-before-fixing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00526 |
| Opus 5 | $0.00019 | $0.00263 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
investigate-before-fixing 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Fixes Without Investigation
When a bug, failing test, or unexpected behavior appears, do not patch the symptom. Find the root cause, then fix it. Symptom-patching creates whack-a-mole debugging, and every fix that doesn't address root cause makes the next bug harder to find.
Sequence
- Prior art. Before hypothesizing, search
docs/solutions/(filenames, Symptom, Tags),docs/learnings.md, and.cadence/learnings.md. Cite any match that fits the current symptoms. - Reproduce. If you can't trigger it deterministically, gather more evidence before forming a hypothesis. Read the stack trace, the relevant code path, and recent diffs touching those files.
- One testable hypothesis at a time, in a single sentence: "X is wrong because Y." Confirm by reading the exact code that would prove it, or by adding a temporary log/assertion — never by guessing from the error string alone.
- 3-strike rule. If three hypotheses fail, stop. The bug is probably structural. Surface to the user: what was tried, what was ruled out, the next two reasonable directions — and add a solution doc per
capture-learnings. - Fix the cause, not the closest symptom. The smallest diff that eliminates the actual problem. Resist refactoring adjacent code in the same commit.
- Regression test that fails without the fix and passes with it. A test that always passes proves nothing. Package as the library evidence bundle per
verify-with-runtime(test_name,red_output,green_output).
Red flags — slow down if you catch yourself doing these
- Proposing a fix before tracing the data flow. You're guessing.
- Each fix reveals a new problem one layer deeper. You're at the wrong layer.
- "Quick fix for now." There is no "for now" — fix it right or hand it back with what you learned.
Lock the blast radius
If the fix would touch more than ~5 files, pause. Either the root cause genuinely spans them (say so), or scope is creeping. Offer to split: critical path now, the rest deferred.
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.
- 12d ago First seen · 30 lines · 38 tokens per session scan A 858ac8c9a65c
investigate-before-fixing is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 526 once invoked, about $0.0002 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.