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 jmagly/aiwg --skill mention-wiregit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/mention-wire)<a href="https://agentmods.dev/skills/jmagly/aiwg/mention-wire"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/mention-wire/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/jmagly/aiwg/mention-wire"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/mention-wire.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 | $0.00014 | $0.00948 |
| Opus 5 | $0.00007 | $0.00474 |
| Sonnet 5 | $0.00003 | $0.00190 |
| Haiku 4.5 | $0.00001 | $0.00095 |
Grade A, and why
mention-wire 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@-Mention Wiring
Analyze codebase relationships and inject @-mentions for traceability.
Research Foundation
- REF-001: BP-9 - Traceability from requirements to code to tests
- Claude Code 2.0.43: @-mention fixes for reliable nested loading
Usage
/mention-wire # Analyze current directory
/mention-wire --dry-run # Show what would be added
/mention-wire --interactive # Approve each mention
/mention-wire --auto # Apply high-confidence mentions
/mention-wire --confidence 90 # Set confidence threshold
Options
| Option | Default | Description |
|---|---|---|
| --target | . | Directory to analyze |
| --dry-run | false | Show proposed changes without applying |
| --interactive | false | Prompt for approval per file |
| --auto | false | Apply mentions above confidence threshold |
| --confidence | 80 | Minimum confidence % for auto mode |
Process
1. Scan Directory
Identify files and their types:
- Source code (
.ts,.js,.py,.go, etc.) - Test files (
*.test.*,*.spec.*,test_*) - SDLC artifacts (
.aiwg/**/*.md) - Documentation (
docs/**/*.md)
2. Analyze Relationships
Detect relationships using heuristics:
| Pattern | Inferred @-mention | Confidence |
|---|---|---|
File in src/auth/ |
@.aiwg/requirements/UC-*-auth*.md |
85% |
File named *test*.ts |
@$AIWG_ROOT/src/{corresponding-source}.ts |
92% |
Comment // UC-001 |
@.aiwg/requirements/UC-001.md |
95% |
Comment // ADR-005 |
@.aiwg/architecture/adrs/ADR-005*.md |
90% |
JSDoc @implements |
Parse and validate | 98% |
| Import statement | @{imported-file} |
88% |
3. Generate Suggestions
Output format:
src/services/auth/login.ts (confidence: 85%)
+ @.aiwg/requirements/UC-003-user-auth.md (name match)
+ @.aiwg/architecture/adrs/ADR-005-jwt-strategy.md (comment: "JWT")
test/integration/auth.test.ts (confidence: 92%)
+ @$AIWG_ROOT/src/services/auth/login.ts (test-to-source)
+ @.aiwg/requirements/UC-003-user-auth.md (inherited from source)
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.
- 9d ago First seen · 137 lines · 14 tokens per session scan A b6ec37c829c7
mention-wire is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 948 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 2026-09-03.
Other skills, from other repositories
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
dos-dispatch
Plan and ship the next batch on one lane: run dos-next-up, acquire a lease with dos arbitrate, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.
dos-class-cycle
Run one DOS plan-class lifecycle tick from the workspace [lifecycle] table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.