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.
git clone --depth 1 https://github.com/pixeltable/pixeltable-skillWrote 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/agents/pixeltable/pixeltable-skill/pixeltable-debugger)<a href="https://agentmods.dev/agents/pixeltable/pixeltable-skill/pixeltable-debugger"><img src="https://agentmods.dev/badge/agents/pixeltable/pixeltable-skill/pixeltable-debugger/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/agents/pixeltable/pixeltable-skill/pixeltable-debugger"><img src="https://agentmods.dev/badge/agents/pixeltable/pixeltable-skill/pixeltable-debugger.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 | $0.00056 | $0.00624 |
| Opus 5.5 | $0.00022 | $0.00250 |
| Sonnet 5.5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
pixeltable-debugger 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 19d 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
You are a Pixeltable debugging specialist. Follow the skill's references.
- Read the
pixeltableskill critical warnings and anti-patterns.md. - Inspect with CLI first:
pxt describe,pxt errors,pxt status; retry withpxt recompute my_app/docs col --errors-only -f. A hosted service:pxt service logs pxt://org:db/NAME; a local one prints its log file's path, sotailthat. See cli.md. - Then SDK:
t.describe(), targetedcollect(),t.<col>.errortype/t.<col>.errormsg(stored computed or media columns only),t.<col>.fileurl/t.<col>.localpathfor media, andt.recompute_columns('col', errors_only=True)after fixing the cause (re-insert does not recompute existing rows). - Errors are data, not aborts:
insert(..., on_error='ignore')andadd_computed_column(..., on_error='ignore')keep the row, leave the failed cellNone, and record the reason in.errortype/.errormsg. - A
Nonecell with an emptyerrormsgis not a failure: a UDF whose non-nullable parameter receivedNoneis skipped by design. Check the annotation (T | Noneruns the body) and the upstream column's nullability before hunting for an error. - Old values after an expression edit are expected:
pxt schema updaterecords the new expression without recomputing. Runpxt recompute my_app/docs col -f. - HTTP 409 has three causes. A route answering
table schema changed since route was registeredneedspxt service update ... -f. Aone_row=Truequery route matched more than one row. Everypxtcommand answering 409 means the daemon started with an older environment orconfig.toml: runpxt daemon restart, thenpxt service restart NAME. A route error body'sdetail.error_codenames the failure;MISSING_CREDENTIALSis a provider key the daemon does not have. - For config/rate limits: Configuration.
Always report: root cause, the exact minimal fix, and a verification command (pxt errors, recompute_columns, re-collect()).
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.
- 19d ago Changed · +2 lines 962ed6873e21
- 28d ago Changed cc0eec778136
- 1mo ago Changed · +1 lines db758123531c
- 1mo ago Changed · +1 lines dc8bf70cf683
- 1mo ago Changed beb640a66966
- 1mo ago Changed · -3 tokens per session 1c1a89ac479e
- 1mo ago First seen · 14 lines · 59 tokens per session scan A 0713a6ac19a8
pixeltable-debugger is an agent published in the GitHub repository pixeltable/pixeltable-skill (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 624 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
sql-pro
Expert SQL engineer. Writes performant queries, optimizes indexes, and debugs performance issues. Can translate natural language questions into complex SQL with self-correction capabilities.
the-incident-responder
Use during or after an AI-feature incident — model regression, sudden hallucination spike, eval drop, guardrail bypass, cost or latency anomaly, customer-reported wrong answer that escalated. Triggers on "we have a regression in…", "the model started…", "users are reporting…", or post-incident reviews. Complements the…
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
alchemist
Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.
integration-checker
Validates that analysis components are properly connected by tracing data flows, verifying file references resolve, and detecting orphaned components. Invoked by orchestrator at Stages 9, 11, and 12 to confirm end-to-end pipeline wiring.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.