Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/yarlson/yarstack/wiki-reconcilenpx skills add yarlson/yarstack --skill wiki-reconcilegit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/wiki-reconcile)<a href="https://agentmods.dev/skills/yarlson/yarstack/wiki-reconcile"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/wiki-reconcile.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00695 |
| Opus 5 | $0.00026 | $0.00347 |
| Sonnet 5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
wiki-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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile Wiki Knowledge
Maintain current understanding without erasing evidence. A candidate is a claim to evaluate, not a fact to append.
Search Before Write
Do not create a file under notes/ until all of these steps succeed:
- Resolve ../../scripts/yarbrain.py relative to this SKILL.md.
- Search by proposed title, entities, aliases, project, and distinctive phrases. Repeat searches and raise the result limit when five results cannot cover every plausible overlap.
- Read every plausible overlap with the helper's read command.
- Compare scope, dates, confidence, volatility, status, and provenance.
If search is unavailable or ambiguous, stop without changing canonical notes.
Reconcile
Choose exactly one operation:
- NOOP when the current note already represents the candidate accurately.
- MERGE when the candidate adds compatible evidence or detail.
- SUPERSEDE when newer evidence replaces a time-sensitive claim.
- SPLIT when different projects, environments, users, or versions explain an apparent contradiction.
- CONFLICT when credible evidence disagrees and cannot yet be resolved.
- CREATE only when no existing note represents the concept.
Draft a focused patch before editing canonical knowledge. Hash the UTF-8 string with SHA-256 and use proposal- as its ID and Markdown filename. Digest the UTF-8 proposal body, excluding its digest field, with SHA-256, then store it beside its candidate under inbox/memory/. Show the operation, every target, search evidence, source episodes, changed current understanding, history effect, and rollback steps. Store unresolved conflicts under inbox/conflicts/. If the current request does not authorize a vault write, show the draft without storing it.
Apply a patch only after explicit approval, including a request that clearly names the reviewed proposal ID and digest. Any proposal change invalidates that approval. For a multi-file change, require a working rollback mechanism and restore the pre-edit state after partial failure. Preserve old provenance and record corrected or superseded claims in History. A canonical note must contain id, kind, scope, status, created, updated, verified_at, volatility, aliases, and sources frontmatter plus Current understanding, Why, Edge cases, Evidence, and History sections when those sections have content.
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.
- 5d ago First seen · 68 lines · 52 tokens per session scan A fb9f63e2da35
wiki-reconcile is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 695 once invoked, about $0.0003 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
lerim
Query Lerim's persistent project context before agent work. Use it to check prior decisions, constraints, preferences, and historical context through exact queries or synthesized answers.
k-knowledge
把稳定项目事实写回 AGENTS.md 或 project-map。触发：收尾、纠偏，或用户说「记住」。.
k-reconcile
以当前代码和正式事实归宿为准，校准项目地图与 Agent 上下文。.
context-engineering
项目级上下文工程框架：通过 PROJECT / REQUIREMENTS / ROADMAP / STATE 四层文档 为每个任务建立结构化上下文，控制 token 预算，防止上下文腐烂， 确保跨会话连续性。与 context-lifecycle 的 L0-L3 层互补。.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…