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 anton-abyzov/specweave --skill sw-projectgit clone --depth 1 https://github.com/anton-abyzov/specweaveWrote 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/anton-abyzov/specweave/sw-project)<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-project"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-project/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/anton-abyzov/specweave/sw-project"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-project.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 | $0.00650 |
| Opus 5.5 | $0.00014 | $0.00260 |
| Sonnet 5.5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
sw-project 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 20d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sw-project: shared intent across tools
Your tool runs the work; SpecWeave keeps what every tool and account must share, in the
repository: the goal (.specweave/project/hub.json), durable decisions
(.specweave/memory/), work items, artifacts and routine definitions.
Steps
- Read AGENTS.md and
.specweave/memory/MEMORY.md, thenspecweave project show --json. No project yet:specweave project init --name "Name" --goal "Goal"(works without Git). - Keep the goal and shared context current with
specweave project set --revision N --goal "..."or--context-file ctx.md. Read the latest revision first; a stale write fails instead of overwriting another session. - Decisions that must outlive this session: one file per fact in
.specweave/memory/and one line for it inMEMORY.md. Never store secrets or a copy of the conversation. - One work item per outcome:
specweave project work-add --title "Outcome" --summary "Scope and expected evidence", reusing existing items. Engineering work links an increment with--increment 0042; its ledger andspecweave verifystay authoritative. - A fresh assignment for another tool:
specweave project brief --intent ID --harness codex(orclaude,generic). It is a snapshot, not proof anything started. - Record who ran it when known:
specweave project work-record --intent ID --revision N --harness codex --session ID. Omit model and effort when unknown. - Deliverables:
specweave project artifact-add --revision N --title "Report" --location reports/report.md --intent ID(files stay in place; HTTPS links work).specweave project work-update --intent ID --revision N --state reviewmarks review readiness; it is not verification. - Routines are definitions:
specweave project routine-add --revision N --title "Weekly review" --cadence "Mondays 09:00" --instructions-file routine.md. Only configure a real scheduler when the user has authorized recurring runs.
Follow your tool's own task and subagent rules and the user's authorization; never
invent a task or session id. specweave dashboard shows the hub, work board and sessions.
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.
- 20d ago First seen · 44 lines · 36 tokens per session scan A 32a44b16b371
sw-project is a skill published in the GitHub repository anton-abyzov/specweave (165 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 650 once invoked, about $0.0001 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 2026-09-26.
Other skills, from other repositories
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
knowledge-session-state-and-context
A codebase guide for storing agent sessions, rebuilding their visible state, recovering active work, branching or rewinding history, and shortening context sent to the model.
sibyl
Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.
geml-vault
Work a Markdown knowledge base — an Obsidian vault, a wiki, a docs tree — by BLOCK ADDRESS instead of by whole page. Use when the job is to find which page and which section says something, read that one section, add a line to an index or a log, or rewrite one section of a note: geml find answers with file#address…
project-context
Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.
doc-harness
A file-based project record system that helps people and AI agents understand and resume ongoing work. It uses documents for current status, file lists, work history, project rules, and optional coordination between projects.