By 88plug
Recover Claude Code sessions after an Anthropic API output-classifier false positive (the "cyber-related safeguards" / "appears to violate our Usage Policy" hard failure). A JSON-aware .jsonl log surgeon that surgically removes the triggering message + refusal turn and re-stitches the parentUuid chain so the session resumes cleanly, cleans accumulated refusals across old sessions, and installs a per-repo CLAUDE.md framing guard to stop recurrence.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Recover a Claude Code session when Anthropic's API output classifier false-positives on legitimate engineering work — and stop it happening again.
A Claude Code plugin for the hard request failure "appears to violate our Usage
Policy / this request triggered cyber-related safeguards" — the one that kills a
turn mid-generation on dense-but-legitimate topics (mining software,
supply-chain/sigstore tooling, payment automation, infra-ops, security infra).
It's a JSON-aware .jsonl log surgeon: it removes the poisoned turns, re-stitches
the session so --resume works, and installs a guard so the next session doesn't
re-trip.
/plugin marketplace add 88plug/claude-code-plugins
/plugin install recover-from-false-positive@88plug
The skill auto-triggers the moment the Usage-Policy / cyber-safeguards error text appears anywhere in the conversation. To run the surgeon directly:
# Fix ONLY the session that just fired (removes the trigger message + refusal,
# re-stitches the chain, backs up first). Resume cleanly afterward.
python3 ${CLAUDE_PLUGIN_ROOT}/skills/recover-from-false-positive/scripts/scrub_refusals.py --fix-active
[!NOTE] Detect-only by default. The script makes a backup tarball before writing and refuses any change that would add a dangling
parentUuid.
--apply to remove accumulated refusal
turns machine-wide. Chain-safe; old sessions stay resumable.## Cyber-safeguard false positives — READ FIRST guard in the right
CLAUDE.md, naming the actual trigger files and vocabulary.The bundled hooks make recovery and prevention hands-free:
StopFailure → detect — when a turn dies on the classifier, a pure-Python
hook reads the live transcript, extracts the trigger vocabulary, pre-classifies
it (project-only vs cross-project), and writes ~/.claude/.fp-state.json. No
model generation, so it can't itself re-trip.UserPromptSubmit → recover — on your next prompt, if that state file
exists, the recovery steps (repair the log, classify with edgar-morin, update
the right CLAUDE.md) are injected and the state file is consumed. It also
always injects a short neutral generation guideline.SubagentStart → frame — every subagent gets the neutral generation
guideline so spawned prompts don't trip; Explore/Plan additionally get the
full CLAUDE.md re-injected (they skip it by default).sed -i '/violate/d'Claude Code .jsonl logs are a linked list — every turn carries a uuid and a
parentUuid pointing at the previous turn. Deleting a line with sed orphans the
next turn (its parentUuid points at a uuid that no longer exists), which breaks
claude --resume. This script re-stitches the chain — rewiring each orphan's
parentUuid up to the removed turn's parent — before dropping lines.
# dry-run first; confirm delta=0 for every file, then apply
python3 ${CLAUDE_PLUGIN_ROOT}/skills/recover-from-false-positive/scripts/scrub_refusals.py
python3 ${CLAUDE_PLUGIN_ROOT}/skills/recover-from-false-positive/scripts/scrub_refusals.py --apply
recover-from-false-positive) with scripts/scrub_refusals.py —
the chain-re-stitching log surgeon — and references/prevention.md, per-repo
CLAUDE.md guard templates (supply-chain/sigstore, mining/PoW, BTCPay/Lightning,
chaos/infra-ops).hooks/hooks.json): detect-false-positive.py (StopFailure),
inject-recovery-context.sh (UserPromptSubmit), inject-subagent-framing.sh
and inject-claudemd-into-subagents.sh (SubagentStart).Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub 88plug/claude-code-plugins --plugin recover-from-false-positiveUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Eyes and hands on a Linux Wayland desktop: screenshot any monitor and click, type, scroll, drag, and read any visible app over xdg-desktop-portal (RemoteDesktop + ScreenCast), with optional OCR + OmniParser icon grounding. Pure-Python, CPU-only. GNOME/Wayland only. Ships the MCP server plus a drive-screen skill that encodes the locate-ground-act-confirm loop.
The sanctioned OS 'motor cortex' for an agent on a Linux box: control systemd services/timers, query journald, read host resources/processes, send desktop notifications, drive D-Bus, and manage power (suspend/reboot/poweroff) — all through structured interfaces (systemctl/loginctl/journalctl/busctl), never raw PID hacks. Pure standard library, zero pip deps. A self-preservation guard refuses severing actions on units the agent depends on (dbus, logind, sshd, network, tailscaled, the session, goosed) unless force=true. Ships the MCP server plus a control-os skill. The system-service counterpart to screen-mcp's GUI control.
Detects when Claude drifts away from your active output contract (a terse persona, hard formatting/length rules, an in-character voice) and quietly steers it back. Each assistant turn is scored by a deterministic, dependency-free engine; a status-line badge shows live drift and the next prompt gets a one-shot correction nudge when the previous reply broke contract.
Seamless context continuity across Claude Code compaction. Four background layers (continuous tool-call capture, mechanical PostCompact handoff, async Opus 4.7 enrichment at --effort max, async Stop-hook refinement, and preemptive snapshot before the next compact) keep the agent's working state intact across every compaction and resume. All summarization is isolated from CLAUDE.md/auto-memory and invisible to the user.
Harness-native ECC plugin for engineering teams - 67 agents, 277 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,846 supported skills.