Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. 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/friedbotstudio/baseline/main/.claude/skills/system-reconcile/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/system-reconcile)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/system-reconcile"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/system-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/friedbotstudio/baseline/system-reconcile"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/system-reconcile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 87 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.01271 |
| Opus 5.5 | $0.00000 | $0.00508 |
| Sonnet 5.5 | $0.00000 | $0.00254 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
system-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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
system-reconcile — corpus health, reported before anything is repaired
Invocable by the user (/system-reconcile) and by Claude (/archive Step 5.5, report-only).
The corpus at docs/system/ accumulates two kinds of drift: the tree moves out from
under the model, and the model grows entries the tree no longer backs. Seven checks
name both directions. The report is the deliverable — repairs are a second,
human-confirmed step, and most runs end after the report.
The one-writer rule
/archive Step 5 is the corpus's only writer on the primary tree. This skill does
not have an apply mode and reconcile-report.mjs exports no writer, so no workflow
phase can reach one through it. When a repair is confirmed, you perform it here in
main context using the writers that already exist — never by adding one to the
report module.
Step 1 — check the flag
node .claude/skills/workspace/cli.mjs flags # gates on memory.architecture_map.enabled — read the `architecture_map:` line
false → stop and tell the user the corpus is not enabled for this project. Every
path below is inert, so running them would print seven empty arrays and read as a
clean corpus rather than an absent one.
Step 2 — run the report
node .claude/skills/system-reconcile/cli.mjs report --json
Nothing is written. docs/system/ is byte-identical afterwards, which is the
property /archive Step 5.5 depends on.
Step 3 — read the seven checks
| Check | What a non-empty result means | The repair, once confirmed |
|---|---|---|
gaps |
A governed-surface file no element anchors. The map is no longer total over what it claims to describe. Reported only — /archive Step 5.5 never gates on it. |
Add an element whose anchor covers it, or widen an existing anchor to a glob. |
stale |
The element's stored anchor_digest no longer matches the file's structural interface — something another file could depend on moved. |
Re-stamp the element after confirming the diagram still describes it. |
dangling |
The anchor resolves to nothing. A broken route, not an unfalsifiable drawing. | Repoint the anchor, or remove the element if the subject is gone. |
duplicateAnchors |
Two ids claim one anchor — usually a merge where each branch derived the same anchor under a different name. | Reported, never auto-resolved: two meanings sharing one anchor cannot be told apart mechanically. Ask which id survives. |
orphanShards |
A .puml section naming no element. The corpus cannot say what the diagram shows. |
Add the missing element, or delete the shard. |
unillustrated |
An element with no shard. Advisory as a severity — a gap in illustration, not a broken model — but /archive Step 5.5 gates on it, so an unillustrated element blocks the next commit until it is drawn. |
Draw it with writeDiagramShard. |
missingKind |
A shard carrying no ' @kind, so witness.bindingFor returns witness: none and the element routes but is never citable as evidence. |
Write the kind the shard already declares structurally with writeDiagramShard. |
What ships with it
3 files 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.
- 1mo ago First seen · 92 lines · 0 tokens per session scan A 75af39e82999
system-reconcile is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,271 tokens. 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 2026-09-03.
Other skills, from other repositories
monitoring-observability
OpenTelemetry, structured logging, distributed tracing, alerting, and dashboards. Use when instrumenting services, designing logs/traces/metrics, defining SLOs and alerts, or debugging production behavior from telemetry.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
diagnose-windows-sandbox-acl
Use on Windows for unexpected ALEGO sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.