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/wubing2023/paperspine/paperspinegit clone --depth 1 https://github.com/WUBING2023/PaperSpineWhat 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 | $0.00012 | $0.00769 |
| Opus 5 | $0.00006 | $0.00385 |
| Sonnet 5 | $0.00002 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
paperspine 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start the PaperSpine workflow for the current project.
Invocation arguments: $ARGUMENTS
If the arguments request update, update check, or auto-update on|off|status, route immediately through the paper-spine skill's
references/update.md. Do not launch intake or start a paper workflow for an
update command.
For every other invocation, run the update playbook's --auto preflight before
intake. If it installs a new version, stop and ask the user to reload Claude
Code and invoke /paperspine again. If it is disabled, not due, already current,
or fails without changing the install, continue with the current version.
After update routing and preflight, if
paper_rewriting_output/paper_spine_config.json is missing or incomplete,
route through the paper-spine skill and launch the PaperSpine intake UI
automatically.
Do not hand-write the configuration.
Platform-specific launcher
Windows
$config = Join-Path (Get-Location) "paper_rewriting_output\paper_spine_config.json"
$launcher = Join-Path $env:USERPROFILE ".claude\skills\paper-spine\scripts\launch_paperspine_ui.ps1"
if (-not (Test-Path -LiteralPath $launcher)) {
throw "PaperSpine UI launcher not found at $launcher. Reinstall or resync PaperSpine."
}
if (-not (Test-Path -LiteralPath $config)) {
powershell.exe -NoProfile -ExecutionPolicy Bypass -File $launcher -OutputDir "paper_rewriting_output"
}
for ($i = 0; $i -lt 120 -and -not (Test-Path -LiteralPath $config); $i++) {
Start-Sleep -Seconds 5
}
if (-not (Test-Path -LiteralPath $config)) {
throw "PaperSpine intake config was not created yet. Finish the opened PowerShell UI window, then rerun /paperspine."
}
Get-Content -LiteralPath $config -Raw
macOS / Linux
CONFIG="paper_rewriting_output/paper_spine_config.json"
LAUNCHER="$HOME/.claude/skills/paper-spine/scripts/launch_paperspine_ui.sh"
if [ ! -f "$LAUNCHER" ]; then
echo "PaperSpine UI launcher not found at $LAUNCHER. Reinstall or resync PaperSpine." >&2
exit 1
fi
if [ ! -f "$CONFIG" ]; then
chmod +x "$LAUNCHER"
bash "$LAUNCHER" "paper_rewriting_output"
fi
for i in $(seq 1 120); do
if [ -f "$CONFIG" ]; then break; fi
sleep 5
done
if [ ! -f "$CONFIG" ]; then
echo "PaperSpine intake config was not created yet. Finish the opened terminal window, then rerun /paperspine." >&2
exit 1
fi
cat "$CONFIG"
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.
- 2d ago First seen · 83 lines · 12 tokens per session scan A 7fa72733dd4e
paperspine is a command published in the GitHub repository WUBING2023/PaperSpine (5,063 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 769 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.