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/phuonghx/aim-cli/systematic-debuggingnpx skills add phuonghx/aim-cli --skill systematic-debugginggit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00090 | $0.00855 |
| Opus 5 | $0.00045 | $0.00428 |
| Sonnet 5 | $0.00018 | $0.00171 |
| Haiku 4.5 | $0.00009 | $0.00085 |
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Guessing is the slowest way to fix a bug. A method that forces you to reproduce, narrow, explain, and confirm — in that order — turns a frustrating hunt into a short walk.
Four stages, in order
Resist the urge to edit code before you reach stage four. Each stage produces evidence that makes the next one cheaper.
Stage 1 — Reproduce it on demand
You cannot fix what you cannot trigger. Pin down the exact path to the failure.
- Write the precise sequence: inputs, actions, environment, expected vs. actual result.
- Record how reliably it fires — every time, most of the time, occasionally, or rarely.
- A flaky repro is itself a clue: it points toward timing, ordering, or shared state.
Stage 2 — Shrink the search space
Cut the problem down until only the culprit remains.
- When did it start? What landed around that time? (
git log, deploy history.) - Does it happen everywhere, or only in one environment?
- Strip the scenario down to the smallest snippet that still fails.
- Bisect: find the single smallest change that flips working to broken.
Stage 3 — Explain the cause, with proof
Chase the why until you hit something that, if changed, makes the bug impossible — not merely something that makes it disappear.
Symptom : the report endpoint returns an empty list for valid users
why? -> the query filters on tenant_id = NULL
why? -> tenant_id is never read from the request
why? -> the middleware that sets it runs after the handler
why? -> route registration order was changed in the last refactor
Root cause: middleware ordering — fix the registration, not the query
Each "why" must rest on observed evidence (a log line, a value, a diff), never on a hunch.
Stage 4 — Fix, then prove the fix
A change is not a fix until you have shown the failure is gone and nothing else broke.
- Confirm the original repro no longer fails.
- Exercise the surrounding behavior to check for collateral damage.
- Add a test that would have caught this, so it cannot quietly return.
- Scan for sibling code with the same mistake.
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 · 95 lines · 90 tokens per session scan A e8c37683a08a
systematic-debugging is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 855 once invoked, about $0.0005 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).