Borrowing it
Nothing to install: this file belongs to ihuzaifashoukat/splicedeck. 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/ihuzaifashoukat/splicedeck/main/.claude/skills/recovering-from-a-refusal/SKILL.mdgit clone --depth 1 https://github.com/ihuzaifashoukat/splicedeckWrote 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/ihuzaifashoukat/splicedeck/recovering-from-a-refusal)<a href="https://agentmods.dev/skills/ihuzaifashoukat/splicedeck/recovering-from-a-refusal"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/recovering-from-a-refusal/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/ihuzaifashoukat/splicedeck/recovering-from-a-refusal"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/recovering-from-a-refusal.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 | $0.00107 | $0.01297 |
| Opus 5 | $0.00053 | $0.00648 |
| Sonnet 5 | $0.00021 | $0.00259 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
recovering-from-a-refusal 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recovering from a refusal
A splicedeck refusal is a successful call that carries its own correction. It is not an error to report and not a wall to work around. Ninety-four codes exist so that recovery is one turn rather than a diagnosis.
The full catalogue, generated from the code, is in references/refusal-codes.md. Read it when you need a specific code. The four rules below are what you need every time.
The four rules
1. When retry_with is non-empty, send one of those calls verbatim.
The server built them from what it already knows — the handles that exist, the bookmarks that are shipped, the rung that is proven. Re-deriving the arguments yourself turns a one-turn recovery into a guessing loop, and you will get it wrong in exactly the places the server would not.
{"ok": false, "refused": "SHEET_NOT_VERIFIED",
"retry_with": [{"verb": "verify", "args": {"sheet": "c1"}}]}
Send verify(sheet="c1"). Do not construct something similar.
2. When needs_human is true, stop and report human_step.
No call you can send fixes it. Saying so plainly is the correct outcome. Inventing a workaround here is worse than stopping, because the workaround usually means disabling the thing that refused.
3. Never install anything in response to a refusal.
FFMPEG_ABSENT does not mean "go and get ffmpeg". This project never installs,
downloads, vendors or bundles ffmpeg — that is a deliberate rule, not an omission,
and docs/first-run.md §4 gives the three reasons. The same holds for
TIER_BINARY_ABSENT. Report the step; the human runs it.
4. A refusal is not a reason to change the plan.
Most refusals mean one call is missing, not that the approach is wrong. Add the call and continue.
The ones you will actually hit
| Code | What it really means | Do this |
|---|---|---|
UNKNOWN_HANDLE |
The handle was never minted here — or, on splice, you passed a source handle where a sheet source key belongs |
inspect first; for splice, read sources[].key out of the sheet |
SHEET_NOT_VERIFIED |
The sheet changed since verify |
run verify again, then retry |
GATE_BLOCKING |
A gate fails, commonly an empty body lane | run verify to see which; splice a segment if the body is empty |
BOOKMARK_UNKNOWN |
No bookmark by that name | retry_with lists the ones that exist; only baseline ships |
UNKNOWN_PARTY |
No directory at casebook/parties/<party>/ |
a human creates it; mkdir is the whole step |
ENCODER_UNPROVEN |
ffmpeg lists it, this machine cannot run it | run trial; never substitute an encoder yourself |
NOT_ON_WORD_EDGE |
A cut edge falls inside a word | retry_with carries two calls, one keeping the word and one excluding it — pick by meaning |
VALUE_NOT_PERMITTED |
An argument carried a value where an identifier belongs, usually a key that looks like a path |
send a plain identifier |
RIGHTS_MISSING |
An asset has no licence record | human step; delivery will not proceed without one |
LANE_DISK_SHORT |
Not enough free space for the planned run | report the numbers; the human frees space |
What ships with it
1 file 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.
- 11d ago First seen · 98 lines · 107 tokens per session scan A 4b96ef4a12d9
recovering-from-a-refusal is a skill published in the GitHub repository ihuzaifashoukat/splicedeck (3 stars, last pushed 24d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,297 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
auto-fix
A bug-fixing workflow that first reproduces a problem with a test, then applies the smallest code change needed. It also checks the related code path and runs tests afterward.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
ast-refactoring
A code-refactoring guide that uses an abstract syntax tree, a structured representation of source code, to make changes based on code meaning rather than text matching.
entropy-scan
A codebase health scan that measures disorder and highlights technical debt, meaning code problems that make future changes slower or riskier. It checks complexity, dependencies, repeated code, file size, and recent change frequency.
auto-doctor
A diagnostic helper for checking whether an agent harness is installed correctly and whether its platform connections are wired up.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.