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/tta-lab/ttal-cli/sp-debuggingnpx skills add tta-lab/ttal-cli --skill sp-debugginggit clone --depth 1 https://github.com/tta-lab/ttal-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 | $0.00021 | $0.00440 |
| Opus 5 | $0.00010 | $0.00220 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
sp-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 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.
What it actually says
Bug Diagnosis and Fix Planning
Diagnose from evidence, then persist the diagnosis and fix plan in FlickNote. Do not implement the fix.
1. Confirm the Symptom
Restate the observed behavior, expected behavior, affected surface, and known reproduction. Ask one focused question if the report is ambiguous.
2. Find the Root Cause
- Reproduce the failure.
- Read the complete errors and logs.
- Check recent changes and working examples.
- Trace bad state backward across component boundaries.
- Form one hypothesis and test it with the smallest useful probe.
If three hypotheses fail, stop and question the model or architecture instead of stacking guesses.
Useful references in this directory:
root-cause-tracing.mddefense-in-depth.mdcondition-based-waiting.md
3. Confirm the Diagnosis
Tell the user:
- Root cause and supporting evidence
- Proposed fix boundary
- Main risk or trade-off
Get alignment before writing a detailed plan when the fix direction is not already approved.
4. Write the FlickNote
Save one note in orientation:
flicknote add --project orientation
Structure:
Fix:
Symptom
Root cause
Evidence and reproduction
Fix strategy
Anti-goals
Implementation stages
Test strategy
Exit criteria
Risks
For behavior fixes, include TDD explicitly:
- Add a focused regression test.
- Run it and confirm it fails for the diagnosed reason.
- Implement the minimum fix.
- Run focused and broader tests.
- Refactor while green.
Each stage must name exact files, commands, expected results, and dependencies.
5. Worker-Eye Check
Re-read the note as the implementer. Fix missing paths, hidden assumptions, unclear ordering, and unresolved decisions with FlickNote edits.
Return the FlickNote ID and a short diagnosis summary. Stop; do not start implementation or invoke another skill.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 74 lines · 21 tokens per session scan A 4edede9945de
sp-debugging is a skill published in the GitHub repository tta-lab/ttal-cli (23 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 440 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…