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 skills add EvolveHQ/docflow --skill workspace-syncgit clone --depth 1 https://github.com/EvolveHQ/docflowWrote 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/evolvehq/docflow/workspace-sync)<a href="https://agentmods.dev/skills/evolvehq/docflow/workspace-sync"><img src="https://agentmods.dev/badge/skills/evolvehq/docflow/workspace-sync/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/evolvehq/docflow/workspace-sync"><img src="https://agentmods.dev/badge/skills/evolvehq/docflow/workspace-sync.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 | $0.00100 | $0.00992 |
| Opus 5.5 | $0.00040 | $0.00397 |
| Sonnet 5.5 | $0.00020 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
workspace-sync 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workspace-sync
Reconcile native returns and keep delivery state honest against checked evidence.
Operating contract
Inputs: canonical workspace root, member roots or remotes, the returned receipt or member state to check, the actor/host permitted to write canonical records, and the scope of the update. Effects: canonical writes to run reconciliation, delivery observations, work criteria evidence, the receipt record and INDEX. It grants no authority, dispatches nothing and never edits a member repository. Native claims / dependencies / resources: observe them at their current native sources; this skill reconciles what already happened, it does not reserve or claim work. Stopping point: a source-bound reconciliation with each changed observation naming the exact revision checked. Receipt: actual reads/checks, the returned or observed evidence, what was updated, what remained unknown, and the refreshed INDEX.
Resolve inputs and current authority
Reuse supplied choices; ask only for a materially missing root, host or scope. A recorded preference is not authority: writing canonical observations needs the current operator mandate or a compatible accepted agreement, and a chat message alone is not evidence. Recheck the exact grant revision, its scope revision, expiry and revocation before accepting a return; a denied action stops across alternate tools and routes. Completed work leaves its still-current agreement accepted. Read the registry, conventions, the current records and the member instructions before writing. Locate the packaged assets as the other workspace skills do; never assume a source checkout.
Reconcile returned receipts
Read the exact returned brief binding, native session/host, actions, checks and receipt before changing anything. Accept a receipt only when its evidence resolves to real native sources at the cited revision. A readiness report for which no attempt started is not a receipt and is never stored as one. Record reconciliation with who checked it, when and against which evidence. Preserve distinct outcomes: passed, failed, skipped, stale and unknown stay distinct; only passed evidence supports completion.
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.
- 9d ago First seen · 85 lines · 100 tokens per session scan A 7f43b71c9c60
workspace-sync is a skill published in the GitHub repository EvolveHQ/docflow (16 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 992 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 2026-10-07.
Other skills, from other repositories
adr-integration
This skill should be used when the user asks about "ADR integration", "ADR CI/CD", "ADR tooling", "ADR automation", "export ADRs", "ADR documentation site", or needs guidance on integrating ADRs with CI/CD, documentation sites, and other tools.
adr-decision-drivers
This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.
adr-fundamentals
This skill should be used when the user asks "what is an ADR", "when should I create an ADR", "ADR best practices", "architecture decision records", "ADR lifecycle", "how to document architecture decisions", or needs guidance on ADR fundamentals, when to create ADRs, or ADR lifecycle management.
adr-quality
This skill should be used when the user asks about "ADR quality", "review ADR", "ADR checklist", "improve ADR", "ADR validation", "good ADR examples", or needs guidance on evaluating, improving, and maintaining high-quality architectural decision records.
adr-compliance
This skill should be used when the user asks about "ADR compliance", "architecture compliance", "ADR audit", "enforce ADRs", "check code against ADRs", "ADR violations", or needs guidance on auditing code compliance with accepted architectural decision records.
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.