Borrowing it
Nothing to install: this file belongs to radiantlogicinc/fastworkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radiantlogicinc/fastworkflow/main/.claude/skills/fastworkflow-failure-archaeology/SKILL.mdgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote 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/radiantlogicinc/fastworkflow/fastworkflow-failure-archaeology)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-failure-archaeology"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-failure-archaeology/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/radiantlogicinc/fastworkflow/fastworkflow-failure-archaeology"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-failure-archaeology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 189 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Memory Poisoning · line 265 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
- medium Excessive Agency · line 332 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00197 | $0.08181 |
| Opus 5 | $0.00098 | $0.04091 |
| Sonnet 5 | $0.00039 | $0.01636 |
| Haiku 4.5 | $0.00020 | $0.00818 |
Grade A, and why
fastworkflow-failure-archaeology 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 10d 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastWorkflow Failure Archaeology
TEAM-PRIVATE: embeds content from uncommitted internal docs. Do not commit or publish this skill without the developer'sexplicit approval.
The chronicle of every major investigation, dead end, revert, and abandoned feature in this repo — so no one re-fights settled battles. Each entry: symptom → root cause → evidence → status. Every commit hash, path, and line number below was verified against the working tree at v2.22.2 (commit c33b9a5) on 2026-07-09.
Prime directive of this skill: before you delete "dead code", revive an "obvious" feature,
or diagnose a "new" bug, check the index below. A spec doc in docs/ is NOT proof a feature
exists; an open beads issue is NOT proof work remains (tracker drift is real, see entry 11);
and a commit titled "Revert" is NOT proof anything was reverted (entry 4).
When to use / when NOT to use
| Situation | Use |
|---|---|
| "Has this been tried/broken/fixed before?" — history lookup | This skill |
| A test/runtime failure is happening NOW and you need triage steps | fastworkflow-debugging-playbook |
| You want the non-negotiable rules and the incidents behind them, to gate a change | fastworkflow-change-control |
| You need the intended design and its invariants | fastworkflow-architecture-contract |
| tau-bench / tau2 mechanics, pass@1 vs pass^k, our benchmark claims | fastworkflow-taubench-reference |
| Running the E0–E25 reliability campaign | tau2-reliability-campaign |
| Statistics for judging whether a "fix" is real (variance, pass^k math) | fastworkflow-proof-and-analysis-toolkit |
| Open research problems built on these failures | fastworkflow-research-frontier |
Index
| # | Entry | Status |
|---|---|---|
| 1 | The payload-loss bug (xray /invoke payload=None) |
settled (v2.21/v2.21.1) |
| 2 | The TurnResult saga: what shipped (v2.21 X6 slice) vs v3.0 roadmap | partly shipped; v3.0 open |
| 3 | fix-85g: the 504-retry double-execution race (v2.22.0 turns engine) | Step 1 settled; Steps 2–3 open |
| 4 | The command_router.py revert trio (the revert that didn't) | moot since v2.6.0 |
| 5 | fix-0hb: the test suite that ate its own trained model | settled (fa97b48) |
| 6 | The RocksDB/speedict removal arc (v2.21.3–v2.21.6) | hot path settled; fix-7kp open |
| 7 | The fingerprint cache-invalidation bug (v2.22.1) | settled (b5747df) |
| 8 | The beads flakiness incident (2026-06-11) | workaround discipline, permanent |
| 9 | The private-doc auto-push incident (2026-07-08) | rule established, permanent |
| 10 | The RLM/tau2 failure taxonomy (Articles 1–3): the variance lesson | open — drives the tau2 campaign |
| 11 | Tracker drift: open beads issues describing shipped work | live caveat |
| 12 | The graveyard: abandoned features and dead code | reference table |
| 13 | Doc-rot register | live caveat |
What ships with it
3 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.
- 10d ago First seen · 398 lines · 197 tokens per session scan A a86c02908a05
fastworkflow-failure-archaeology is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 197 tokens to every session and 8,181 once invoked, about $0.0010 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
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.