Chalk Labs
Need help deploying reconify-engine-ci?
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/reconifyhq-reconify-engine-ci
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
Use cases: devops
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 and code. 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/reconify-engine-ci
What's inside
- Skill name
reconify-engine-ci- Description
- Automate Reconify in CI. Use when producing deterministic artifacts, mapping reconciliation outcomes to job status, or retaining failure evidence.
- License
- MIT
- Instructions
- 65 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Reconify Engine CI ## 1. Define the contract and policy Run `reconify capabilities` for the binary installed in CI. Choose whether unmatched rows or all exception events—including financial-effect and settlement differences—should fail the job, and record the corresponding flag and exit codes from that contract. This checkpoint is complete when config failures and reconciliation-policy failures have separate handling. ## 2. Produce a complete artifact ```bash reconify reconcile --config reconify.yaml --pair PAIR \ --format json --result-mode all --deterministic --out result.json \ --fail-if-exceptions ``` Add `--audit` when provenance is required. Supply `--audit-fixed-timestamp RFC3339` when identical inputs must produce byte-identical artifacts. Keep the config in version control beside the workflow. ## 3. Preserve the Engine exit code GitHub Actions runs shell steps with fail-fast behavior, so capture the status before applying the job policy: ```bash set +e reconify reconcile --config reconify.yaml --pair PAIR \ --format json --result-mode all --deterministic --out result.json \ --fail-if-exceptions status=$? set -e case "$status" in 0) echo "clean" ;; 2) echo "configuration failure" >&2; exit 1 ;; 3|4) echo "reconciliation differences" >&2; exit 1 ;; *) echo "unexpected Engine failure: $status" >&2; exit "$status" ;; esac ``` Verify these codes against `capabilities` when adopting a different Engine protocol version. To gate the agent deliverables themselves, run `reconify --agent verify` after the artifacts exist. Exit `0` is clean (skipped checks are not failures). Exit `2` with `CONFIG_INVALID` is a config failure handled like the reconcile case above; exit `2` with `VERIFICATION_FAILED` means a deliverable is stale or inconsistent: treat it as a job failure and retain the verification output with the artifacts. Name `--result` and `--explanation` explicitly in CI so a missing artifact fails instead of being skipped. When financial checks are configured, retain `financial_effect_diff` and `settlement_diff` events in the failure artifact. `financial_unchecked` is informational and does not fail the job by itself; `--fail-if-exceptions` fails for financial and settlement differences as well as ordinary exceptions. ## 4. Retain evidence on failure Upload `result.json` with the CI platform's always-run condition so policy failures retain the artifact that explains them. For large inputs, read `../reconify-engine-performance/SKILL.md` and choose a streaming artifact plus explicit retention limits. CI work is complete when the same commit and inputs reproduce the artifact, every opted-in exit code has a deliberate job outcome, and failure evidence remains downloadable.
From reconifyhq/reconify, MIT.
More from reconifyhq/reconify
- 0.626score
reconify-engine-debug
reconifyhq
Diagnose unexpected Reconify results.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-reconcile
reconifyhq
Reconcile unfamiliar financial files end to end.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-bootstrap
reconifyhq
Bootstrap a Reconify workspace.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-cli
reconifyhq
Resolve Reconify CLI behavior from the installed binary.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-config
reconifyhq
Configure Reconify from real input files.
SkillAFreshness: A★ 8Claude Code +9 - 0.587score
reconify-engine-performance
reconifyhq
Fit Reconify runs within resource limits.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-performance
reconifyhq
Compatibility alias for reconify-engine-performance.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-config
reconifyhq
Compatibility alias for reconify-engine-config.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-debug
reconifyhq
Compatibility alias for reconify-engine-debug.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-cli
reconifyhq
Compatibility alias for reconify-engine-cli.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-bootstrap
reconifyhq
Compatibility alias for reconify-engine-bootstrap.
SkillBFreshness: B★ 8Claude Code +9 - 0.547score
reconify-ci
reconifyhq
Compatibility alias for reconify-engine-ci.
SkillBFreshness: B★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 3
- Open issues
- 13
- Last commit (this folder)
- Oct 7, 2026 (23 days ago)
- Last release
- Aug 29, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/reconifyhq/reconify
- Website
- docs.reconifyhq.com/cli
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from reconifyhq
- 0.626score
reconify-engine-debug
reconifyhq
Diagnose unexpected Reconify results.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-reconcile
reconifyhq
Reconcile unfamiliar financial files end to end.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-bootstrap
reconifyhq
Bootstrap a Reconify workspace.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-cli
reconifyhq
Resolve Reconify CLI behavior from the installed binary.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
reconify-engine-config
reconifyhq
Configure Reconify from real input files.
SkillAFreshness: A★ 8Claude Code +9 - 0.587score
reconify-engine-performance
reconifyhq
Fit Reconify runs within resource limits.
SkillBFreshness: B★ 8Claude 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 reconify-engine-ci 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
reconify-engine-ci skill. Agent Mart. https://agentmart.dev/skills/reconifyhq-reconify-engine-ci (last updated 2026-10-24)