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 AcKeskin/contexture --skill work-stategit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/work-state)<a href="https://agentmods.dev/skills/ackeskin/contexture/work-state"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/work-state/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/ackeskin/contexture/work-state"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/work-state.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 | $0.00134 | $0.02700 |
| Opus 5 | $0.00067 | $0.01350 |
| Sonnet 5 | $0.00027 | $0.00540 |
| Haiku 4.5 | $0.00013 | $0.00270 |
Grade A, and why
work-state 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-state
The scope chain's lifecycle-state driver. One question — where is this slug, and what's next? — answered as structured data computed from the filesystem, not narrated. The chain keeps real per-slug state on disk (vision / spec+INDEX / plan+spec-pin / blueprint / archive); /work-state <slug> reads that state and reports it the same way every time, machine-checked.
Governed by leverage-over-ceremony: replace the multi-directory hand-walk ("list specs, read INDEX, check the plan's pin, infer execute from recap") with one command, instant answer. The expensive part (is an artefact's content good enough) stays the model's/human's job — /work-state does only the cheap, deterministic part.
Where it sits. /checkpoint asks is it good; /work-state asks where is it / what's next. /update-changelog records what shipped (past); /work-state reports where in-flight work stands (present). /close-out closes a slug; /work-state reports when a slug has reached the close. Distinct lenses — /work-state is the one that's purely positional and purely deterministic.
When to run
- User types
/work-state <slug>or/status <slug>(explicit). - User asks "where is
<slug>in the chain", "what's the next step for<slug>", "is<slug>'s plan stale", "did I ever execute<slug>". - Do not auto-fire. Mode A, user-invoked. Read-only — it never writes, never mutates an artefact (the one inviolable property; see "What it does NOT do").
The chain and its dependency graph
The fixed stage order and what each stage depends on (the graph the resolver computes over):
| Stage | Artefact on disk | Depends on |
|---|---|---|
| vision | .claude/visions/<slug>/ (active version via its INDEX, if present) |
— |
| spec | .claude/specs/<slug>/ active version (.claude/specs/INDEX.md) |
vision (soft — a spec can exist without a vision) |
| plan | .claude/plans/<slug>/ active version, with a spec: frontmatter pin |
spec |
| blueprint | .claude/docs/<slug>/ active version (optional stage) |
plan (soft — blueprint is optional) |
| execute | no artefact of its own | plan |
| archive | .claude/archive/<date>-<slug>/ (the close-out terminus) |
execute |
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 · 115 lines · 134 tokens per session scan A 60b33caf35df
work-state is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 2,700 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
customer-success
Support workflows, ticketing systems (Zendesk, Intercom), knowledge base design, chatbot design, and metrics (CSAT, NPS). Use when building support infrastructure, designing help centers, or optimizing customer experience.
event-planner
Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.
hr-talent
HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building, succession planning, and D&I programs. Use when hiring, managing performance, designing organizations, or building culture.
innovation
Innovation management expertise for innovation frameworks (Design Thinking, Stage-Gate), ideation processes, innovation portfolio management, venture capital, open innovation, and IP strategy. Use when driving innovation, managing R&D portfolios, or building innovation programs.
agent-teams
Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns.
workflow-status
Read-only workflow sensor: compute repository, roadmap, dependency, PR, finding, and recovery state, then emit the fixed machine envelope. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next", "state of the run".