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 OutlineDriven/outline-driven-development --skill build-program-graphgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/build-program-graph)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/build-program-graph"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/build-program-graph.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.02273 |
| Opus 5 | $0.00024 | $0.01137 |
| Sonnet 5 | $0.00010 | $0.00455 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
build-program-graph 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a program graph
A program graph turns a source tree into nodes (functions, methods, types, modules, contracts) and edges (calls, inheritance, imports, containment) that queries can answer: who calls this sink, what can this entrypoint reach, where do trust levels change across a call. This skill builds the graph for the whole tree, runs the preanalysis passes that security queries depend on, and reports evidence with its version and parser limits attached. Reachability answers where a call path exists; it never proves that attacker-controlled data flows anywhere.
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user needs a multi-language source graph for call paths, attack surface, entrypoints, blast radius, coarse taint reachability, boundaries, types, proxies, or declared cross-system links. |
| Authority | Reversible local: writes only graph exports, preanalysis subgraphs and annotations, and an optional declared-links file; rollback is deleting the written files. No remote mutation. The graph tool must already be installed; this skill never installs or upgrades tooling. |
| Side effect | Graph export files, preanalysis subgraphs and annotations (in-memory), and an optional declared-links file at the analysis root. Rollback: delete the written files; in-memory annotations vanish when the engine is disposed. |
| Done | The correct languages are parsed, preanalysis has run, requested queries return evidence with the version and parser limits stated, and no reachability result is presented as data-flow or vulnerability proof. |
Inputs
- Required: A target directory containing source code to parse.
- Optional: An explicit language list when the target is known polyglot or single-language; otherwise use the tool's auto-detection. An existing declared-links file for cross-boundary edges. An external binary-analysis graph export for augmentation where the tool supports it.
Refusals
- Will not present call-graph reachability or taint-subgraph membership as data-flow or vulnerability proof.
- Will not fall back to manual analysis when the graph tool is unavailable or fails; manual reading misses what the graph catches.
- Will not invent a supported language list, a versioned method, or a cross-boundary edge.
- Will not treat proxy or binary-origin nodes as source code functions.
What ships with it
1 file 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.
- yesterday Changed · -39 tokens per session 865903fe7ae1
- 4d ago First seen · 85 lines · 88 tokens per session scan A f2473d8f5506
build-program-graph is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,273 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
optimize
Use when asked to optimize code, speed up a path, reduce allocations, repair a regression, or profile a target. Not for remote, credential, publish, deploy, or irreversible changes.
debug
Hypothesis-driven debugging. Use when a test fails, a crash or exception occurs, output is wrong, or an intermittent flake has no obvious cause.
ios-build-fix
Use when asked to run /ios-build-fix to fix a failing iOS build, regenerate an Xcode project from project.yml, or correct UI behavior. Not for a clean rebuild: use ios-build-cleanup.
strike-the-root
Use when a bug, failure, flake, regression, review finding, or ticket needs the core fixed so it cannot recur. Not for greenfield features: use tdd. Not for style-only review or typo-class one-liners.
extremely-optimize
Use when asked to run a performance campaign against a measured floor. Not for hypothesis-only analysis without mutation: use fastopt.