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 sssstwee/tastedistill --skill tasted-debuggit clone --depth 1 https://github.com/sssstwee/tastedistillWrote 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/sssstwee/tastedistill/tasted-debug)<a href="https://agentmods.dev/skills/sssstwee/tastedistill/tasted-debug"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/tasted-debug/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/sssstwee/tastedistill/tasted-debug"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/tasted-debug.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 | $0.00062 | $0.00593 |
| Opus 5.5 | $0.00025 | $0.00237 |
| Sonnet 5.5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
tasted-debug 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 2mo 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.
This is a copy
91% identical to debug — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug: Prove The Cause
Use this skill when the task starts from a symptom.
Prefix your first response line with ⚗️ inline, not as its own paragraph.
Before the workflow, apply ../../shared-rules/personalization.md for explicit TasteD/TasteDistill invocations.
Apply ../../shared-rules/runtime-hygiene.md when debugging uses helper scripts, browser checks, local servers, screenshots, traces, or other generated artifacts.
Outcome Contract
- Outcome: proven root cause, minimal fix or handoff, and verification evidence.
- Done when: every observed symptom fits the explanation and the fix is checked by a reproducible test or runtime observation.
- Evidence: repro steps, logs, traces, state, source paths, generated artifacts, tests, screenshots, and command output.
Workflow
- List the observed symptoms.
- Reproduce the issue or define the missing evidence.
- Trace from symptom to source.
- State a one-sentence root-cause hypothesis with evidence.
- Make the smallest fix that addresses the cause.
- Run the narrow regression check.
- Search for the same bug shape if the root cause is reusable.
Coding Guardrails
For fixes, apply ../../shared-rules/coding-guardrails.md:
- Think before coding: do not edit until the root-cause hypothesis is specific and evidence-backed.
- Simplicity first: fix the cause directly; avoid broad rewrites, new abstractions, or speculative compatibility.
- Surgical changes: keep the patch to the failure path; search siblings only for the same bug shape.
- Goal-driven execution: prove the original symptom changed with a reproducible check.
CodeGraph
For root-cause analysis in a Git repository, ../../shared-rules/personalization.md should already have ensured the local CodeGraph index. When codegraph_* tools are available, prefer codegraph_trace for "how does X reach Y", codegraph_callers / codegraph_callees for one-hop flow, and codegraph_context for nearby implementation context. Read target files directly before editing.
What ships with it
1 file 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.
- 2mo ago First seen · 61 lines · 62 tokens per session scan A 76a3a5b76e5a
tasted-debug is a skill published in the GitHub repository sssstwee/tastedistill (2 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 593 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to debug, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
smart-explore
Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
ix
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
hivemind-graph
Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems exist?", "what's the impact of…
honcho-cli
Inspect and debug Honcho workspaces via the honcho CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
property-repro
Reproduce a reported Honcho API bug (a 5xx, a wrong status code, data that doesn't round-trip) as a failing Hypothesis/Schemathesis test, then fix it. Use when an issue reports an unexpected API error, when hunting for 5xx bugs in a route, or before changing request validation or error handling.
rca
Root-cause analysis for code. Use when a defect shipped and was caught after the fact, a run came back BLOCKED or a deliverable failed validation, a bug recurs after a prior fix, or the user says 'rca this', 'root cause this', 'postmortem this', or 'why did this break'. Produces a structured RCA that separates surface…