Borrowing it
Nothing to install: this file belongs to aigengame/cli-agentic-workflow. 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/aigengame/cli-agentic-workflow/main/.agents/skills/reconcile/SKILL.mdgit clone --depth 1 https://github.com/aigengame/cli-agentic-workflowWrote 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/aigengame/cli-agentic-workflow/reconcile)<a href="https://agentmods.dev/skills/aigengame/cli-agentic-workflow/reconcile"><img src="https://agentmods.dev/badge/skills/aigengame/cli-agentic-workflow/reconcile/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/aigengame/cli-agentic-workflow/reconcile"><img src="https://agentmods.dev/badge/skills/aigengame/cli-agentic-workflow/reconcile.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 | $0.00099 | $0.01079 |
| Opus 5.5 | $0.00040 | $0.00432 |
| Sonnet 5.5 | $0.00020 | $0.00216 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
reconcile 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 2mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile
Keep the cross-referenced web of issues + domain docs (CONTEXT.md, docs/adr/) correct
and consistent so the development feedback loop stays trustworthy. A decision discussed in a
session must not silently drift out of sync with the issues and docs that record it.
Read first: docs/agents/domain.md (glossary + ADR-conflict rules), docs/agents/issue-tracker.md
(gh conventions), docs/agents/triage-labels.md. See REFERENCE.md for the
reference-graph edge taxonomy and the full check catalog.
Triggers
- Manual: invoked as
/reconcile, or when the user asks to sync issues and docs. - Automatic: a Claude Code Stop hook (and optionally a
gitpre-commit hook) may auto-invoke this skill — see "Hook setup" below. Hook wiring is HITL; never add it without user approval.
Safety posture (non-negotiable)
Report first, mutate only after confirmation. Always present findings and proposed patches,
then wait for the user to confirm before editing any doc file or GitHub issue. Never run a
mutating gh issue edit / gh issue comment or write to a doc without explicit approval.
Workflow
gather change set → build reference graph → check (mechanical + semantic) → report → confirm → apply + propagate
1. Gather the change set
The semantic layer is driven by the current conversation context. Identify the decision / requirement changes discussed in-session: which terms were renamed, which decisions reversed or refined, which scope/Phase boundaries moved. Write them down as an explicit change list. If the session contains no such change, run the mechanical layer only and say so.
If the user states a change explicitly, use that verbatim as the change set.
2. Build the reference graph
Load the artifacts and extract their cross-references (see REFERENCE.md for edge types and how to read each source):
- Issues + PRDs —
gh issue list/view(Parent, Blocked by,ADR-NNNN,#NN, domain terms) - ADRs —
docs/adr/*.md(ADR-NNNNcross-refs,status:front-matter, domain terms) CONTEXT.mdglossary — canonical terms and their_Avoid_synonyms;ADR-NNNNrefs
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.
- 2mo ago First seen · 87 lines · 99 tokens per session scan A 1cafe861929b
reconcile is a skill published in the GitHub repository aigengame/cli-agentic-workflow (20 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,079 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
reconcile compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reconcileaigengame/cli-agentic-workflow | Skill | 20 | 4mo ago | MIT | A | 99 | Claude Code, Codex |
| slipway-runsignalridge/slipway | Skill | 24 | 4d ago | BSD-3-Clause | A | 25 | Claude Code |
| slipway-decomposesignalridge/slipway | Skill | 24 | 4d ago | BSD-3-Clause | A | 20 | Claude Code |
| slipway-proposesignalridge/slipway | Skill | 24 | 4d ago | BSD-3-Clause | A | 22 | Claude Code |
| awslXhinLiang/awsl | Skill | 96 | 1mo ago | Apache-2.0 | A | 63 | Codex |
| slipway-workflowsignalridge/slipway | Skill | 24 | 4d ago | BSD-3-Clause | A | 41 | Claude Code |
| hyalo-skillsractive/hyalo | Skill | 27 | today | MIT | A | 26 | Codex |