Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/docxology/templatenpx agentmods add skills/docxology/template/pipeline-debuggingWrote 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/docxology/template/pipeline-debugging)<a href="https://agentmods.dev/skills/docxology/template/pipeline-debugging"><img src="https://agentmods.dev/badge/skills/docxology/template/pipeline-debugging/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/docxology/template/pipeline-debugging"><img src="https://agentmods.dev/badge/skills/docxology/template/pipeline-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.00940 |
| Opus 5.5 | $0.00041 | $0.00376 |
| Sonnet 5.5 | $0.00021 | $0.00188 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
template-pipeline-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 13d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline debugging
Natural invoke
- "My pipeline failed at PDF render for template_code_project"
- "Project Analysis finishes in under a second with no figures — help debug"
- "run.sh --pipeline failed; what's the first real error?"
- "Resume from checkpoint after fixing project tests"
Inputs to confirm
- Project — from
docs/_generated/active_projects.md; infer from context if obvious. - Invocation — full vs
--mode core,--resume,--skip-infra, multi-project. - Failing stage — if unknown, reproduce first.
Workflow
-
Reproduce — re-run the failing invocation verbatim; capture full stderr/stdout and exit status. Quote the first real error, not the last line. Name the failing stage (setup, infra tests, project tests, analysis, render, validate, LLM review, LLM translations, copy).
-
Isolate — run that stage's underlying command directly (pytest target, analysis script, validation CLI, renderer). Use
--resumeto skip good upstream stages while iterating. -
Classify — dependency/uv gap, missing system tool (LaTeX/pandoc-crossref), nondeterministic input, coverage gate, undefined citation/cross-ref, thin-orchestrator violation (logic in
scripts/notsrc/), or logic bug. When Project Analysis completes in under a second with no figures, treat as import/dependency failure and isolate viascripts/pipeline/stage_02_analysis.py. Trace where bad state enters; fix at ingestion. -
Fix minimally — re-run full pipeline green; confirm
--resumeshows no upstream regression. Updateprojects/<n>/AGENTS.md/README.mdif the failure mode was non-obvious.
Deliverables
- Failing stage, first real error (quoted), root cause, minimal patch (file + snippet).
- Exact commands + raw exit status proving green.
- Do not claim "fixed" without a clean full-pipeline run.
Verification commands
uv sync
uv run python scripts/runner/execute_pipeline.py --project <project>
uv run python scripts/runner/execute_pipeline.py --project <project> --resume
uv run python scripts/runner/execute_pipeline.py --project <project> --mode core
uv run python scripts/pipeline/stage_01_test.py --project <project>
uv run pytest projects/<project>/tests/ --cov=projects/<project>/src --cov-fail-under=90 -q
uv run python -m infrastructure.validation.cli prerender projects/<project>/manuscript --repo-root .
uv run python -m infrastructure.validation.cli pdf --project <project> --repo-root .
uv run python -m infrastructure.rendering.latex_package_validator
LOG_LEVEL=0 uv run python scripts/runner/execute_pipeline.py --project <project> --resume
What ships with it
2 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.
- 13d ago Changed 28e5ded92156
- 1mo ago First seen · 76 lines · 103 tokens per session scan A dd3a20f54dcc
template-pipeline-debugging is a skill published in the GitHub repository docxology/template (20 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 940 once invoked, about $0.0004 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 skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
orca-replay
Answer questions about an earlier agent run from its recording rather than from memory, and replay or fork that run. Use when the user asks why a previous run did something, which step changed a file or broke the build, whether yesterday's failure still reproduces, or whether a different model would have got it right.
auto-service-technician
Use when a task needs senior auto-service-technician judgment — diagnosing a check-engine-light or drivability complaint from DTCs and live data, deciding whether a code-named part actually needs replacing or the fault lies upstream, scoping a flat-rate repair order and labor time, choosing warranty vs. customer-pay…
commercial-industrial-electronics-repairer
Use when a task needs the judgment of a Commercial and Industrial Electronics Repairer — diagnosing a VFD fault trip on a production line, tracing a PLC I/O fault back to the sensor, the wiring, or the ladder logic, selecting arc-flash PPE for live-panel diagnostic work, triaging multiple simultaneous down-lines by…
computer-user-support-specialist
Use when a task needs the judgment of a Computer User Support Specialist — triaging an inbound ticket's severity and SLA clock before troubleshooting it, verifying a caller's identity before any password/MFA/account-state change, walking a live incident through a structured troubleshooting sequence instead of guessing…
control-valve-installer-repairer
Use when a task needs the judgment of a Control and Valve Installer/Repairer — sizing a control valve's Cv against actual process flow, diagnosing a limit-cycling control loop as valve stiction versus a bad PID tune, running an FCI 70-2 seat-leakage or API 598 pressure test, calibrating a positioner/actuator after a…