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/outlinedriven/outline-driven-development/ast-grepnpx skills add OutlineDriven/outline-driven-development --skill ast-grepgit 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/ast-grep)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/ast-grep"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/ast-grep.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01227 |
| Opus 5 | $0.00028 | $0.00613 |
| Sonnet 5 | $0.00011 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
ast-grep 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ast-grep
Contract
| Field | Bound contract |
|---|---|
| Trigger | AST-based modification, structural search, lint, or replacement too fragile for regex. |
| Authority | Reversible local writes to VCS-tracked source files only. Search is read-only; rewrites apply only through the helper after dry-run review. Roll back via version control. |
| Side effect | Local file writes through the helper two-pass validate/dry-run/apply flow; no remote, credential, or published mutation. |
| Done | Pattern validated, blast radius reviewed, and rewrite landed at the correct scope. |
Inputs
- An ast-grep pattern, single-quoted in the shell so
$VARreaches ast-grep unexpanded. - A language (
--lang) or a single target path whose extension auto-detects it; required for stdin patterns. - For rewrites: a rewrite template and one or more target paths (defaults to the current directory).
- Optional: include/exclude globs (repeatable, prefix
!to exclude), context lines, JSON output mode.
Procedure
- Confirm the task is structural (call, function, class, or import shaped like a pattern), not text/regex/filename matching (use grep) or semantic type/reference lookup (use LSP or the compiler). ast-grep matches syntax, not bytes. Done when: the task is confirmed structural.
- Validate the pattern before searching:
python3 scripts/ast_grep_helper.py validate '<pattern>' --lang <L>. Exit 0 means ast-grep parses it cleanly; exit 2 means malformed (the helper prints the parsed pattern tree showing the ERROR node). Fix and re-validate. Done when: validate exits 0. - For a rewrite, run the dry-run:
python3 scripts/ast_grep_helper.py replace '<pattern>' '<rewrite>' --lang <L> <paths>. Read the diff and theN matches across M filescount. If the blast radius is wrong, stop and refine the pattern (tighten meta-variables, add--lang, add context); re-run the dry-run. Done when: the dry-run diff and match count are correct. - Apply only after the dry-run diff is correct:
python3 scripts/ast_grep_helper.py replace '<pattern>' '<rewrite>' --lang <L> <paths> --apply. The helper writes via a separate--update-allpass. Done when: files are updated via--update-all. - Invoke
ast-grep, neversg:sgcollides with thesetgroupsbinary on many systems. Done when:ast-grepis invoked, notsg.
What ships with it
13 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.
- agents/openai.yaml 164 B
- references/cli.md 1.2 KB
- references/core-concepts.md 2.5 KB
- references/pattern-syntax.md 2.0 KB
- references/pitfalls.md 6.8 KB
- references/project-setup.md 1.7 KB
- references/recipes.md 8.0 KB
- references/rewriting.md 1.7 KB
- references/rule-config.md 2.5 KB
- references/utility-rules.md 1.4 KB
- references/yaml-reference.md 1.8 KB
- scripts/ast_grep_helper.py 15 KB runs code
- tests/smoke.sh 3.1 KB runs code
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 · 51 lines · 57 tokens per session scan A ff045ffe3959
ast-grep is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,227 once invoked, about $0.0003 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
fin-brief-generator
根据用户输入或已有研究输出（文献综述/想法报告/新颖性报告），自动生成或更新FINBRIEF.md，减少用户填写负担。.
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
deps-upgrade
Use when dependency upgrades need tiered batches for CVEs, a major release, forced compatibility, scheduled hygiene, a pre-release lockfile audit, or a cadence-driven or vulnerability-triggered sweep. Classifies each update on a risk ladder, verifies it, or defers it with a reason. Not for PR queue triage; use…
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
strict-validation-setup
Use when a user invokes a strict-mode validation or verifiable-goals loop setup. Bootstraps strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify. Don't use for remote, credential, publish, deploy, or irreversible changes.