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/rse/ase/ase-spec-editnpx skills add rse/ase --skill ase-spec-editgit clone --depth 1 https://github.com/rse/aseWrote 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/rse/ase/ase-spec-edit)<a href="https://agentmods.dev/skills/rse/ase/ase-spec-edit"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-spec-edit.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 | $0.00047 | $0.05582 |
| Opus 5 | $0.00023 | $0.02791 |
| Sonnet 5 | $0.00009 | $0.01116 |
| Haiku 4.5 | $0.00005 | $0.00558 |
Grade A, and why
ase-spec-edit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
@${CLAUDE_SKILL_DIR}/../../meta/ase-format-meta.md @${CLAUDE_SKILL_DIR}/../../meta/ase-format-spec.md @${CLAUDE_SKILL_DIR}/../../meta/ase-tenets.md @${CLAUDE_SKILL_DIR}/../../meta/ase-common-grill.md
Procedure
This skill is plan-less: it never composes or persists a task plan
and MUST NOT call ase_task_save(...). Instead, it applies the
requested edit in place, so the implementing state requires Edit
and Write to modify the affected artifacts. Every modification MUST
stay restricted to the SPEC artifacts the edit actually demands -- the
kinds CODE, DOCS, TASK, INFR, and OTHR are never touched.
On finishing the state <arg1/>, only output the following ,
which shows the established and , where a still
empty or renders as (none):
WHAT:
HOW:
-
Initialize:
-
Set (with any leading and trailing whitespace stripped), set and (both empty), and set (empty). Do not output anything.
-
If is not a positive integer, only output the following and then immediately STOP processing the entire current skill:
-
-
Iterate:
Perform the states (1) querying, (2) discovering, (3) grilling, (4) implementing, and (5) verifying below as one iteration. Without
--loopperform exactly one iteration. Under--looprepeat the iteration until the querying state receives aSTOP SKILLresult. Do not output anything in this item. -
State: querying:
-
-
In the following, you MUST NOT use your built-in tool! Instead, you MUST just show a custom dialog according to the expanded
custom-dialogdefinition. You MUST closely follow this definition. Its only answer option is the fixedSTOP SKILL, so the user normally answers with the edit query in one free-text reply: -
If is
STOP SKILLorCANCEL, only output the following and then immediately STOP processing the entire current skill:Otherwise, strip any leading
OTHER:prefix from and set to the remainder.
-
-
Convert the fresh into -- the domain-specific, non-implementation-detail information -- and -- the remaining information -- discarding all / content of any previous iteration. Without
--grillyou MUST NOT ask any clarifying questions and during later implementation just interpret the query best-effort. Do not output anything.
-
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.
- 4d ago First seen · 521 lines · 47 tokens per session scan A 365996ae44fe
ase-spec-edit is a skill published in the GitHub repository rse/ase (47 stars, last pushed 7d ago), licensed Apache-2.0. It adds 47 tokens to every session and 5,582 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 2026-08-30.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…