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 laurigates/claude-plugins --skill document-linkinggit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/document-linking)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/document-linking"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/document-linking/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/laurigates/claude-plugins/document-linking"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/document-linking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.02590 |
| Opus 5.5 | $0.00019 | $0.01036 |
| Sonnet 5.5 | $0.00009 | $0.00518 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
document-linking 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 18d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Linking
Provides a unified ID system connecting PRDs, ADRs, PRPs, work-orders, GitHub issues, commits, and PRs. IDs are project-scoped, auto-generated on first access, and maintained bidirectionally.
When to Use This Skill
| Use this skill when... | Use blueprint-sync-ids instead when... |
|---|---|
| You need bidirectional links between PRD/ADR/PRP/issue at runtime | You're doing a one-shot bulk ID assignment for docs missing IDs |
| You're auto-assigning an ID on first document access | You want a --dry-run preview of bulk ID changes |
| You want to validate broken cross-document references | Use blueprint-adr-validate instead for ADR-only relationship checks |
| You need to find orphan docs/issues across the project | Use document-detection instead when capturing a brand-new doc |
ID Format
| Document Type | Format | Example | Notes |
|---|---|---|---|
| PRD | PRD-NNN |
PRD-001 |
3-digit, zero-padded |
| ADR | ADR-NNNN |
ADR-0003 |
4-digit (matches existing convention) |
| PRP | PRP-NNN |
PRP-007 |
3-digit, zero-padded |
| Work-Order | WO-NNN |
WO-042 |
3-digit, matches work-order number |
Frontmatter Schema
All blueprint documents should include these fields:
---
id: PRD-001 # Unique identifier (auto-generated if missing)
relates-to: # Cross-document references (optional)
- ADR-0003
- PRP-002
github-issues: # Linked GitHub issues (optional)
- 42
- 87
implements: # For PRPs: source PRD (optional)
- PRD-001
# ... existing fields (created, modified, status, etc.)
---
ID Registry (manifest.json)
IDs are tracked in docs/blueprint/manifest.json:
{
"id_registry": {
"last_prd": 3,
"last_prp": 7,
"documents": {
"PRD-001": {
"path": "docs/prds/user-authentication.md",
"github_issues": [42, 87],
"title": "User Authentication"
},
"ADR-0003": {
"path": "docs/adrs/0003-database-choice.md",
"github_issues": [],
"title": "Database Choice"
},
"PRP-002": {
"path": "docs/prps/oauth-integration.md",
"github_issues": [45],
"implements": ["PRD-001"],
"title": "OAuth Integration"
}
},
"github_issues": {
"42": ["PRD-001", "PRP-002"],
"45": ["PRP-002"],
"87": ["PRD-001"]
}
}
}
What ships with it
2 files 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.
- 18d ago Changed · -100 lines 877ca2855b33
- 1mo ago First seen · 437 lines · 47 tokens per session scan A cf43f2f0aa51
document-linking is a skill published in the GitHub repository laurigates/claude-plugins (59 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 2,590 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
delegation-brief
Before delegatetask: brief the subagent, then verify it.
work-ledger
Multi-day or multi-session work: a ledger that survives.
ticket-delivery
End-to-end ticket workflow from analysis through investigation, planning, TDD implementation, commits, and PR creation, adapted to your setup by saved config. Use when starting work on a ticket or implementing a feature from ticket to PR.
backlog-compiler
Converts a PRD, ticket, or feature description into a .code-virtuoso/loop/backlog.json plan sized and ordered for autonomous loop execution. Use when preparing work for the iteration-loop skill, turning a written ticket into a loop-ready backlog, or when asked to turn a spec into a backlog.
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and…
spec-driven-development
Turns an approved idea or ticket into spec, plan, and task files saved in the repo, then executes them one task at a time with a progress log. Use to write a spec, plan a feature, break work into tasks, or resume multi-session work.