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 tmusser/ai-engineering-skills --skill workspace-checkpointgit clone --depth 1 https://github.com/tmusser/ai-engineering-skillsWrote 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/tmusser/ai-engineering-skills/workspace-checkpoint)<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/workspace-checkpoint"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/workspace-checkpoint/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/tmusser/ai-engineering-skills/workspace-checkpoint"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/workspace-checkpoint.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 | $0.00036 | $0.00971 |
| Opus 5 | $0.00018 | $0.00485 |
| Sonnet 5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
workspace-checkpoint 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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Checkpoint
Purpose
Re-center the next consequential action on the few current constraints and evidence that can change it.
Reactivate, do not introspect. This skill externalizes decision-relevant state; it does not ask the model to reveal private reasoning or claim access to internal representations.
Checkpoint, do not summarize. Read only the highest-authority sources needed for the next action and carry forward the smallest useful active set.
When to use
Use only at a real decision boundary where a buried or competing constraint could change the next action, for example:
- before weakening or rewriting a test, fixture, or compatibility seam
- before widening an API, schema, dependency, permission, or write scope
- before an irreversible or shared-state mutation
- before declaring success when evidence is mixed or incomplete
- before the first consequential edit after a resume or handoff
- after repeated failures when the next attempt risks drifting from the original contract
Skip routine edits, ordinary tool calls, and already-bounded steps whose governing constraint is obvious and current.
A long conversation by itself is not a trigger. Use context-check for context drift, tool-noise-guard for repetitive tool envelopes, verify-contract for proof, and handoff for continuation state.
Inputs
- Exact next action and target
- Current user request and project instructions
- Current task artifacts such as
SPEC.md,VERIFY.md, orHANDOFF.mdwhen relevant - Directly governing code, tests, schemas, or other authoritative references
- Hard constraints, non-goals, compatibility seams, evidence, and stop conditions that can change the next action
Workflow
- Name the exact next action. Do not checkpoint an entire project or phase.
- Read the smallest authoritative source set needed to govern that action.
- Select only constraints and evidence that can change what happens next. Prefer 1-3 governing constraints.
- Emit at most the six-line checkpoint block below.
- If sources materially conflict, do not silently reconcile them. Stop or route to the smallest skill that can resolve the conflict, such as
mini-spec,scope-freeze, or a human decision. - Take the named action immediately once the checkpoint is coherent.
- Treat the checkpoint as expired when the action completes, the evidence changes, or the governing source changes. Recompute only at the next real decision boundary.
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.
- 10d ago First seen · 100 lines · 36 tokens per session scan A 45008b0ae217
workspace-checkpoint is a skill published in the GitHub repository tmusser/ai-engineering-skills (4 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 971 once invoked, about $0.0002 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
awsl
Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.
dwi-all-in-one
Apply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.
dwi-arc
Structure genuinely multi-agent coding work into bounded cells with one writer per scope, explicit integration, and independent review. Use when several disjoint workstreams justify coordination. Do not use for small tasks, overlapping writers, speculative agent fleets, or process artifacts without demonstrated value.
dwi-bridge
Coordinate bounded work between native Claude and Codex workflows with explicit authority, scope, and evidence. Use for read-only consultation or explicitly authorized execution delegation. Do not create a new connector, share secrets, treat messages as authorization, or allow recursive delegation.
dwi-budget
Set and report practical token, context, time, tool-call, and coordination boundaries for coding-agent work. Use when resource use is unclear or needs a checkpoint. Do not invent measurements, monetary savings, cache benefit, or precision that the harness does not expose.
dwi-evidence
Label coding-agent claims by evidence status, preserve provenance and failures, and separate static, runtime, and human proof. Use before completion, comparison, promotion, or handoff. Do not upgrade observations into guarantees or fabricate missing measurements and approvals.