Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
“Handle cascading data retrieval tool failures by falling back to embedded knowledge generation”
Install Cascade Failure Recovery
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace cascade-fail-recovery --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .claude/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .claude/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recoveryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace cascade-fail-recovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .agents/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .agents/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace cascade-fail-recovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .cursor/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .cursor/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/cascade-fail-recovery--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace cascade-fail-recovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .gemini/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .gemini/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HKUDS/OpenSpace cascade-fail-recoveryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .github/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .github/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/OpenSpace cascade-fail-recovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/cascade-fail-recovery .opencode/skills/cascade-fail-recovery && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cascade-fail-recovery" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/cascade-fail-recovery into .opencode/skills/cascade-fail-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cascade-fail-recovery", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cascade-fail-recovery- GitHub stars
- 7.8k
- Token cost
- ~765 tokens
- SKILL.md length
- 253 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
- Works in 4 steps: Recognize Cascading Failure → Preserve Task Context → Invoke Fallback Strategy → …
- SKILL.md covers Purpose, When to Apply, Recovery Procedure and Example Application, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Cascade Failure Recovery is a skill in HKUDS/OpenSpace (7.8k stars). Its SKILL.md is about 765 tokens, with 1 other file in the folder. Licence: MIT.
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3827781. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cascade Failure Recovery loads about 765 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 253 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 253 words, ~765 tokens.
Download SKILL.mdSave it as
.claude/skills/cascade-fail-recovery/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- cascade-fail-recovery
- description
- Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Cascade Failure Recovery
Purpose
When multiple data retrieval tools (read_webpage, search_web) fail in succession, immediately fall back to generating content from embedded knowledge rather than attempting repairs or abandoning the task. This preserves task context and ensures completion.
When to Apply
Use this pattern when you observe:
- 2+ consecutive failures from data retrieval tools
- Network/access errors preventing web content retrieval
- Risk of task abandonment due to tool errors
Recovery Procedure
Step 1: Recognize Cascading Failure
Identify the failure pattern:
Iteration N: read_webpage failed - connection error
Iteration N+1: search_web failed - timeout/unavailable
Iteration N+2: [risk] Agent may abandon task or switch objectivesStep 2: Preserve Task Context
Before switching strategies, explicitly restate the original objective:
ORIGINAL OBJECTIVE: [Restate the core task goal]
CONTEXT PRESERVED: [Key requirements, constraints, deliverables]Step 3: Invoke Fallback Strategy
Immediately switch to embedded knowledge generation:
- Acknowledge the limitation: Note that external data sources are unavailable
- Activate internal knowledge: Use pre-trained knowledge relevant to the task
- Generate content: Use write_file to create the deliverable from available knowledge
- Document the fallback: Note in the output what information could not be verified externally
Step 4: Execute write_file
Generate the required document:
# Fallback to generating from embedded knowledge
write_file(
path="output/document.md",
content="[Generate content from internal knowledge base]"
)Example Application
Scenario: PACT Act veterans benefits document needed, but web access failing
Wrong approach (observed failure):
Iter 11: read_webpage failed - access error
Iter 12: search_web failed - unavailable
Iter 13: [ABANDONED] Switched to unrelated musician payroll taskCorrect approach (with this skill):
Iter 11: read_webpage failed - access error
Iter 12: search_web failed - unavailable
Iter 13: CASCADE FAIL DETECTED - invoking fallback
Iter 14: write_file - generate PACT Act document from embedded knowledge
- Note: "External verification unavailable; content based on training knowledge"Guidelines
- Threshold: Trigger fallback after 2 consecutive retrieval failures
- No endless retries: Do not attempt more than 1 repair/retry cycle
- Preserve objective: Never switch to unrelated tasks when tools fail
- Transparency: Clearly mark any content that lacks external verification
- Document limitations: Note what could not be verified due to tool failures
Related Skills
write-file-fallback: Generate documents when data sources unavailabletask-context-preservation: Maintain objective continuity through errors
© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in benchmarks/gdpval/skills/cascade-fail-recovery of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Cascade Failure Recovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cascade Failure Recovery this skillHKUDS/OpenSpace | 7.8k | — | ~765 | Automated safety check: Pass | MIT | |
| Show Me Your Work Decision Logcursor/plugins | 11k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Scope Creep Guardlennney/stop-that-shit | 2.5k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Verification Before Completionfarm-fe/farm | 5.6k | 47 repos | ~1k | Automated safety check: Pass | MIT | |
| PUA High-Agency Governancetanweai/pua | 20k | — | ~502 | Automated safety check: Pass | MIT | |
| Loop Change Verifiercobusgreyling/loop-engineering | 11k | 1 repos | ~709 | Automated safety check: Pass | MIT |
Similar skills
- Official
Scope Creep Guard
lennney/stop-that-shit
Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.
Verification Before Completion
farm-fe/farm
A skill your agent uses when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…
PUA High-Agency Governance
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
Loop Change Verifier
cobusgreyling/loop-engineering
Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.
Incremental Implementation
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
More from HKUDS/OpenSpace
All 199 skills in this repoAudio Track Production Workflow
HKUDS/OpenSpace
Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.
Sandbox Code Execution Fallback
HKUDS/OpenSpace
Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.
Code Execution Fallback
HKUDS/OpenSpace
A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.
Code Execution Fallback and Path Anchoring
HKUDS/OpenSpace
Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.
Code Execution Fallback E81068
HKUDS/OpenSpace
Fallback workflow for executing Python code when executecodesandbox fails repeatedly
Context Anchored Fallback Report
HKUDS/OpenSpace
Generate documents with writefile when retrieval tools fail, with explicit guardrails against task context drift
Related
Categories
Questions about Cascade Failure Recovery
How do I install Cascade Failure Recovery in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/cascade-fail-recovery in HKUDS/OpenSpace) into .claude/skills/cascade-fail-recovery in your project. Claude Code loads it when a task matches its description.
How do I install Cascade Failure Recovery in Codex?
Run `npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/cascade-fail-recovery in HKUDS/OpenSpace) into .agents/skills/cascade-fail-recovery in your project. Codex loads it when a task matches its description.
Can I use Cascade Failure Recovery in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/OpenSpace --skill cascade-fail-recovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cascade-fail-recovery, .gemini/skills/cascade-fail-recovery, .github/skills/cascade-fail-recovery and .opencode/skills/cascade-fail-recovery in your project.
What does Cascade Failure Recovery need to run?
SKILL.md names no scripts, command-line tools or credentials: Cascade Failure Recovery is instructions for the agent only.
Does Cascade Failure Recovery access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Cascade Failure Recovery safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cascade Failure Recovery use?
Cascade Failure Recovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cascade Failure Recovery use?
About 765 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cascade Failure Recovery?
Skills that share tags, products or a category with Cascade Failure Recovery: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Scope Creep Guard (lennney/stop-that-shit, 2.5k stars), Verification Before Completion (farm-fe/farm, 5.6k stars) and PUA High-Agency Governance (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cascade Failure Recovery?
HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,754 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.
Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.