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 agentmods add commands/anton-abyzov/specweave/ado-pullgit clone --depth 1 https://github.com/anton-abyzov/specweaveWhat 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 | $0.00023 | $0.03355 |
| Opus 5 | $0.00012 | $0.01677 |
| Sonnet 5 | $0.00005 | $0.00671 |
| Haiku 4.5 | $0.00002 | $0.00335 |
Grade A, and why
ado-pull 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 yesterday.
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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADO Pull Command
Usage: sw-ado:pull [target] [options]
Purpose: Pull latest changes from Azure DevOps (like git pull)
Quick Start
# Pull for current/active increment (simple mode)
sw-ado:pull
# Pull for specific increment
sw-ado:pull 0005
# Pull ALL changes across ALL projects (living docs sync)
sw-ado:pull --all
# Pull for specific project/board
sw-ado:pull --project clinical-insights
# Pull specific feature hierarchy (Epic → Feature → User Stories)
sw-ado:pull --feature FS-042
Sync Modes
Mode 1: Increment Sync (Default)
sw-ado:pull [increment-id]
Syncs ONE increment ↔ ONE linked work item.
Mode 2: Living Docs Sync (Full)
sw-ado:pull --all [--time-range 1M]
Syncs ALL specs across ALL projects/boards:
- Discovers all linked specs in
.specweave/docs/internal/specs/ - Fetches changes from ADO for each linked item
- Updates User Stories, Features, Epics
- Respects multi-project folder structure
Mode 3: Project-Scoped Sync
sw-ado:pull --project clinical-insights
Syncs all specs within a specific project folder:
specs/clinical-insights/
├── FS-042/us-001.md ← Synced
├── FS-042/us-002.md ← Synced
└── FS-043/us-003.md ← Synced
Mode 4: Feature Hierarchy Sync
sw-ado:pull --feature FS-042
Syncs a specific feature and ALL its children:
ADO Epic #100
└── Feature #200 (FS-042) ← Synced
└── US-001 #201 ← Synced
└── US-002 #202 ← Synced
└── US-003 #203 ← Synced
What Gets Pulled
| Field | Behavior |
|---|---|
| Status | External ALWAYS wins (QA/stakeholder decisions) |
| Priority | External wins (stakeholder prioritization) |
| Iteration/Sprint | Updated if changed in ADO |
| Comments | New team comments imported |
| Assignee | Updated if changed |
| Parent Links | Epic → Feature → Story hierarchy preserved |
Multi-Project Routing
When pulling with --all, the system routes changes to correct folders:
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.
- yesterday First seen · 489 lines · 23 tokens per session scan A 4d83a39ffead
ado-pull is a command published in the GitHub repository anton-abyzov/specweave (159 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 3,355 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
/add-claude-rule
Appends the rule from $ARGUMENTS to CLAUDE.md.
implement-regression-tests
Implement regression tests marked with it.skip.
read-issue
Fetch and read a GitHub issue using gh command.
add-debug-logs
Add console.log statements to code for debugging.