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 gpsaggese/helpers --skill bookmark.addgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/bookmark.add)<a href="https://agentmods.dev/skills/gpsaggese/helpers/bookmark.add"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/bookmark.add/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/gpsaggese/helpers/bookmark.add"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/bookmark.add.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 | $0.00015 | $0.00530 |
| Opus 5.5 | $0.00006 | $0.00212 |
| Sonnet 5.5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
bookmark.add 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.
What it actually says
Goal
- Given one or more links
<LINKS>, find the file(s) among the following that are related to each link, and add a TODO to the most related file:research/ideas/*.mdwebsite/docs/blog/posts/*.md
// TODO(gp): incorporate the link <LINK> to <TOPIC>
Workflow
Collect Material
- Read the title and content of each link in
<LINKS>(useWebFetchif the URL alone is not descriptive enough to judge the topic) - List all candidate files in the two dirs above
Match Links to Files
- For each link, compare its topic with each candidate's title, headers, and first paragraph. Rank candidates by relevance
- Pick the single best match for each link
- If several files are close, list them and ask the user which to use
- If no file plausibly matches, do not force a match. Report it instead
Add the TODO
- In the matched file, add one line:
where// TODO(gp): incorporate the link <LINK> to <TOPIC><TOPIC>is a short description (under 15 words) of the relevant part of the link, e.g., a technique, a result, or a quote - Placement:
- If the file has a top-of-file
// TODO(gp): ...block, add the new line as an adjacent line in that block - Otherwise, put it near the most related section, e.g., right above the relevant bullet point or paragraph
- If the file has a top-of-file
- Change no other content in the file
- If several links map to one file, add one TODO line per link
Report
- For each link, print the file it was added to and the exact TODO line inserted
- Report any unmatched link explicitly. Do not skip it silently
Verification
- Each link matches at most one file, with no forced or guessed match
- Each inserted line follows the exact
// TODO(gp): incorporate the link <LINK> to <TOPIC>format - No content other than the new TODO line(s) changed in the matched file
- The report lists every link with its target file or "not matched" status
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 · 54 lines · 15 tokens per session scan A 06c1a45a6068
bookmark.add is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 530 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 2026-11-06.
bookmark.add compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bookmark.addgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 15 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |