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 skills/facebook/agentic-tools/search-docsnpx skills add facebook/agentic-tools --skill search-docsgit clone --depth 1 https://github.com/facebook/agentic-toolsWhat 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 | $0.00036 | $0.00618 |
| Opus 5 | $0.00018 | $0.00309 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
search-docs 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Docs
Search the Meta Developer Platform documentation to answer API questions, find integration guides, and explore platform capabilities.
Workflow
-
Start tracking. Before any other work, call
devtools_skill_invocationwith actionstartandskill_namesearch-docs. Passskill_namesearch-docson everydevtools_*tool call in the following steps. -
Understand the query. Determine what the user is looking for:
- API reference (e.g., "how does the Page API work?")
- Integration guide (e.g., "how to set up Instagram webhooks?")
- Troubleshooting (e.g., "why am I getting error code 190?")
- Feature discovery (e.g., "what can I do with the WhatsApp Business API?")
-
Search. Call
devtools_discoverywith actionsearch_docs:- Formulate a clear, specific query
- Start with
max_resultsof 5 - If results are too broad, refine the query and search again
-
Present results. For each result:
- Title and brief description
- Direct relevance to the user's question
- Key takeaways or next steps
-
Refine if needed. If initial results don't answer the question:
- Try alternative search terms (e.g., "Graph API permissions" instead of "Facebook API access")
- Use pagination via
offsetto explore more results - Broaden or narrow the query based on what was returned
-
Synthesize. Don't just list links — extract the answer:
- Summarize the relevant documentation
- Highlight key requirements, limitations, or gotchas
- Provide code patterns or configuration steps if applicable
-
End tracking. After completing all preceding steps, call
devtools_skill_invocationwith actionendandskill_namesearch-docs.
Search Tips
- Use product-specific terms: "WhatsApp Business API" not "WhatsApp API"
- Include the specific operation: "create ad campaign" not "ads"
- For error codes, search the exact code: "error 190" or "OAuthException"
- For permissions, include the permission name: "pages_read_engagement permission"
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 · 56 lines · 36 tokens per session scan A 95d252037467
search-docs is a skill published in the GitHub repository facebook/agentic-tools (5 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 618 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…