reset-strikes
Reset the current session's strike counter to 0 and clear the recorded violation list.
Skill by devseunggwan
Chalk Labs
Need help deploying reset-strikes?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/devseunggwan-reset-strikes
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/reset-strikes
What's inside
- Skill name
reset-strikes- Description
- Reset the current session's strike counter to 0 and clear the recorded violation list. Required after a 3rd strike block before Claude can respond again.
- License
- MIT
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Praxis Strike Reset
Clear the session strike counter so the discipline signals restart from 0.
## What to do
1. Run the strike counter reset via the Bash tool:
```bash
"${CLAUDE_PLUGIN_ROOT}/hooks/strike-counter.sh" reset
```
2. Report the output verbatim. If the session was blocked at 3/3, acknowledge the reset and confirm that future responses will proceed normally until a new strike is declared.
## Reflection gate at 3/3
When the session is blocked at 3/3, reset is **conditional on a written reflection + an explicit user trust decision**.
The strike/stop-hook output names an exact file path (`$STATE_DIR/${SID}.reflection.md`) and the required content structure (violations summary, root cause per violation mapped to a specific rule — project `CLAUDE.md` / `AGENTS.md`, `ETHOS.md`, or the user's global `CLAUDE.md` — preventive checklist). Recovery is a two-step process:
1. **Reflection file** — written by Claude, gates the file check. If missing or empty when reset is called, the script prints `❌ Reset refused — reflection missing or empty.` and re-states the path and required contents. The counter is not cleared.
2. **Persuasion turn** — before the user invokes this skill, Claude must present the reflection in-chat (quote or summarize, do not just point at the path), acknowledge each violation's harm, state concrete behavioral commitments, and explicitly ask the user to run `/praxis:reset-strikes`. This is a trust decision, not a mechanical unlock — the user may decline and require more.
Additional behavior:
- On a successful 3/3 reset, the reflection file is removed alongside the state so the next cycle starts clean and cannot reuse a stale document.
- Below 3/3, reset is not gated — the reflection + persuasion requirement only applies at the block threshold.
## Reinforcement after reset
- Do not treat reset as absolution — the violations happened. Briefly summarize what went wrong this session (if known from the transcript) and state one concrete behavioral adjustment before continuing with user work.
- Do not request a reset on behalf of the user — only execute when the user explicitly invokes this skill.From devseunggwan/praxis, MIT.
More from devseunggwan/praxis
- 0.592score
stale-pr-revival
devseunggwan
Bring an open, stalled pull request back to a mergeable state without rewriting its history — read every review surface, merge the base in, integrate what…
SkillAFreshness: A★ 1Claude Code +9 - 0.588score
codex-review-wrap
devseunggwan
Worktree-aware wrapper for /codex:review.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
upstream-bug-report
devseunggwan
Take a defect in an installed third-party plugin, server, or library from local diagnosis to an issue on its public repository — prove the fix in a fresh…
SkillAFreshness: A★ 1Claude Code +9 - 0.585score
retrospect
devseunggwan
Session retrospect — analyze the current Claude Code session against the rules it ran under (project and global `CLAUDE.md`), identify friction patterns and…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
surface-enumeration
devseunggwan
Pre-implementation input-surface enumeration — before writing a parser/validator/sanitizer/classifier, enumerate every input variant so each becomes a…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
strike
devseunggwan
Declare a rule violation in the current Claude Code session.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
strikes
devseunggwan
Show the current session's strike count (0-3) and the list of recorded violation reasons.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
perf-leak-review
devseunggwan
Point at performance-defect and memory-leak candidates in a diff — a read-only LLM reviewer reads the change plus the repository around it and reports…
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
tradeoff
devseunggwan
Score the options at a decision fork on four cost axes — reversibility, blast radius, cost-if-wrong, process cost — with a provenance grade on every cell so a…
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
merge-briefing
devseunggwan
On-demand home for the pre-merge approval procedure — the three-surface pre-ask probe, grading every open finding by its blocking decoration, carrying the…
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
worktree-merge-cleanup
devseunggwan
On-demand home for the pre-merge worktree precondition and the unified post-merge cleanup sequence — how to run `gh pr merge --squash --delete-branch` from…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
cmux-recover-sessions
devseunggwan
Bulk recover Claude Code sessions after a crash, power loss, OOM kill, or reboot by scanning the .jsonl files Claude Code persists automatically.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 9, 2026 (1 month ago)
- Last release
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/devseunggwan/praxis
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from devseunggwan
- 0.592score
stale-pr-revival
devseunggwan
Bring an open, stalled pull request back to a mergeable state without rewriting its history — read every review surface, merge the base in, integrate what…
SkillAFreshness: A★ 1Claude Code +9 - 0.588score
codex-review-wrap
devseunggwan
Worktree-aware wrapper for /codex:review.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
upstream-bug-report
devseunggwan
Take a defect in an installed third-party plugin, server, or library from local diagnosis to an issue on its public repository — prove the fix in a fresh…
SkillAFreshness: A★ 1Claude Code +9 - 0.585score
retrospect
devseunggwan
Session retrospect — analyze the current Claude Code session against the rules it ran under (project and global `CLAUDE.md`), identify friction patterns and…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
surface-enumeration
devseunggwan
Pre-implementation input-surface enumeration — before writing a parser/validator/sanitizer/classifier, enumerate every input variant so each becomes a…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
strike
devseunggwan
Declare a rule violation in the current Claude Code session.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get reset-strikes running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
reset-strikes skill. Agent Mart. https://agentmart.dev/skills/devseunggwan-reset-strikes (last updated 2026-10-24)