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 zekiriabd/SDD-Pro --skill debugging-failed-pipelinegit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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/zekiriabd/sdd-pro/debugging-failed-pipeline)<a href="https://agentmods.dev/skills/zekiriabd/sdd-pro/debugging-failed-pipeline"><img src="https://agentmods.dev/badge/skills/zekiriabd/sdd-pro/debugging-failed-pipeline.svg" alt="Measured on agentmods" 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 | $0.00143 | $0.01676 |
| Opus 5 | $0.00072 | $0.00838 |
| Sonnet 5 | $0.00029 | $0.00335 |
| Haiku 4.5 | $0.00014 | $0.00168 |
Grade A, and why
debugging-failed-pipeline 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 3d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Debugging a Failed SDDPro Pipeline
Auto-trigger : pipeline RED détecté ou rapporté par utilisateur. Anti-pattern strict : ne JAMAIS "réparer le code" sans avoir lu le rapport du gate qui a produit le RED. Le rapport contient déjà le diagnostic + suggestion FIX (3 lignes
ERROR/CAUSE/FIXavec classe d'erreur préfixée[CLASS]).
Procédure 4 phases (emprunt superpowers systematic-debugging)
Phase 1 — Investigation racine (avant tout fix)
-
Lire le message d'erreur mot à mot. Pas de scan rapide. Pas d'hypothèse "je sais ce que c'est". Lire la classe d'erreur entre crochets.
-
Reproduire : que le Tech Lead relance la commande, ou lire le rapport disque (toutes les erreurs sont persistées 3L).
-
Vérifier les changements récents :
git log --oneline -10 git diff HEAD~1Beaucoup de pipelines RED viennent d'un changement récent (stack.md modifié, US éditée sans re-validate, lib ajoutée hors §2.4).
-
Identifier le gate qui bloque :
/sdd-status {n} # tree ASCII : quel phase est en échec /sdd-help {n} # guidance "what's next" basée sur l'état
Phase 2 — Lire le bon rapport
Selon la classe d'erreur dans le chat :
Classe [CLASS] |
Rapport à lire | Action FIX |
|---|---|---|
[BUILD_CORRECTIBLE] |
stdout build dans chat (3L ERROR) | déjà itéré par build_loop (max BuildLoopMaxIter). Si exhausted → lire stack trace. |
[BUILD_BLOCKING] |
stdout build_loop dans chat (3L ERROR) | fail-fast — problème structurel (DI cycle, layer violation). Pas de retry. |
[QA_TEST_FAILED] |
query_console_db.py feat-stats --feat {n} --format md |
tests failing → fix code OU fix test. Pas les deux en même temps. |
[QA_COVERAGE_GAP] |
query_console_db.py coverage --feat {n} --format md |
ajouter tests dans *.Tests/Unit/ (jamais baisser CoverageMin sans tracer). |
[API_GATE_RED] |
query_console_db.py api-gate --feat {n} --format md |
mismatch contrat back↔front. Re-run /dev-backend {n}-{m} puis /qa-generate {n} --mode api-tests. |
[SPEC_AC_NOT_VERIFIED] (Stage A gate) |
workspace/.sys/.validation/{n}-spec-compliance.md |
AC non implémenté → /dev-{backend|frontend} {n}-{m} sur l'US fautive. |
[REVIEW_*] (code-reviewer Stage B) |
workspace/.sys/.validation/{n}-code-review.md |
issue qualité → fix manuel ou ré-exec dev-* après modif. |
[SEC_*] hard-blocking |
workspace/.sys/.validation/{n}-security-scan.md |
secrets / SQL injection / SSRF → fix immédiat, pas de bypass. |
[STACK_LIBRARY_MISSING] |
chat error 3L | Tech Lead arbitre — éditer .libs.json puis sync_stack_md.py. |
[FEAT_HASH_MISMATCH] |
chat error 3L | re-run /us-generate {n} (idempotent, recalcule hash). |
[PLAN_STALE] |
chat error 3L | re-run /dev-plan {n} puis /dev-run {n}. |
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.
- 3d ago First seen · 104 lines · 143 tokens per session scan A 13979d2f5245
debugging-failed-pipeline is a skill published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 4d ago), licensed Apache-2.0. It adds 143 tokens to every session and 1,676 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.