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 deepskyai/agent-tools --skill approach-briefinggit clone --depth 1 https://github.com/deepskyai/agent-toolsWrote 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/deepskyai/agent-tools/approach-briefing)<a href="https://agentmods.dev/skills/deepskyai/agent-tools/approach-briefing"><img src="https://agentmods.dev/badge/skills/deepskyai/agent-tools/approach-briefing/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/deepskyai/agent-tools/approach-briefing"><img src="https://agentmods.dev/badge/skills/deepskyai/agent-tools/approach-briefing.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 | $0.00167 | $0.01811 |
| Opus 5.5 | $0.00067 | $0.00724 |
| Sonnet 5.5 | $0.00033 | $0.00362 |
| Haiku 4.5 | $0.00017 | $0.00181 |
Grade A, and why
approach-briefing 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 2mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approach Briefing Generator
Converts an instrument-approach plate into a structured briefing. No external dependencies required in default mode — the agent uses its own vision.
When to invoke
- The user shares an image or PDF of an approach plate.
- The user asks to "brief the approach", "what are the mins", "what's the missed", "which transition", "read this plate", or similar.
- The user compares two plates at the same airport ("ILS vs RNAV for 28R").
- The user supplies a plate URL from d-TPP, Jeppesen, or an AIP.
Extraction workflow
Follow these three steps in order. Do not skip step 1.
Step 1 — Verify the plate
Before extracting anything, confirm:
- Airport & runway match what the user asked about (ICAO ID + runway).
- Procedure title matches (e.g. "ILS OR LOC RWY 28R", "RNAV (GPS) RWY 13").
- Effective date / cycle is current. If the plate shows an AIRAC cycle older than today, warn the pilot: the plate may be out of date.
If any of these is off, stop and ask the user to confirm before briefing.
Step 2 — Extract into the JSON schema
Fill in every field of references/briefing-schema.json that is present on
the plate. Use null for anything not shown. Consult
references/plate-reading-guide.md for where each field typically lives on
FAA / Jeppesen / ICAO AIP layouts. Specific gotchas:
- Frequencies — include only frequencies published on the plate. Distinguish approach, tower, ground, ATIS/AWOS, CTAF as applicable.
- Minima — extract every published line (S-ILS, S-LOC, CIRCLING, LPV, LNAV/VNAV, LNAV) with DA/MDA and visibility for each category (A/B/C/D). Do not average or invent values.
- MSA — note the reference fix and sector altitudes. If the MSA is a
single 25 NM circle, mark
sectored: false. - Missed approach — extract as a single string of the plate's written
instructions plus structured
holding(fix, inbound course, leg time or distance, turn direction). - Notes — capture every boxed or asterisked note verbatim. These often contain cold-temperature corrections, DME substitutions, circling restrictions, or NOTAM references.
- Units — keep whatever units the plate uses (ft / m / nm / km). Do not convert silently.
What ships with it
3 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.
- 2mo ago First seen · 145 lines · 167 tokens per session scan A 0c112d68f2f8
approach-briefing is a skill published in the GitHub repository deepskyai/agent-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 167 tokens to every session and 1,811 once invoked, about $0.0007 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 2026-08-31.
approach-briefing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| approach-briefingdeepskyai/agent-tools | Skill | 2 | 4mo ago | MIT | A | 167 | Claude Code, Codex |
| onekgpdK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 143 | Claude Code |
| biopythonK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 65 | Claude Code |
| experimental-designK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 201 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 44 | Claude Code |
| neuropixels-analysisK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 99 | Claude Code, Codex |
| pkpd-modelingK-Dense-AI/scientific-agent-skills | Skill | 57k | yesterday | MIT | A | 273 | Claude Code |