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 XRenSiu/claude-code-forge --skill spec-compilegit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/spec-compile)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/spec-compile"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/spec-compile.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 | $0.00342 | $0.04642 |
| Opus 5 | $0.00171 | $0.02321 |
| Sonnet 5 | $0.00068 | $0.00928 |
| Haiku 4.5 | $0.00034 | $0.00464 |
Grade A, and why
spec-compile 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-compile
Compile any spec — a 常驻不变量 invariant or a 本次验收 done_when clause — into a standard a gate can
run. One compiler, three production lines, routed by decidability, not by level. This
skill describes the decidability ladder the routing rides on, what each line emits, the
disciplines that keep each line load-bearing, and the exit that proves a clause was pushed as
far down as it could go. It prescribes no step order — the engine sequences the work; what
follows are the gaps to fill and the gates that must hold, in any order.
术语映射（在 sdlc 里怎么读这份文件）
本 skill 引自 qanat 仓库，正文保留其领域词汇；在 sdlc 里按下表读：
| 原文 | sdlc 里的对应物 |
|---|---|
| Territory（领地） | 一个 bounded context / 模块：dos.yaml 的 bounded_contexts.current_context；issue 的 Depends on DOS 所属上下文 |
| Run（一次执行） | 一次 issue → PR 的交付，即 .sdlc/<slug>/ 一个 slug |
| Contract / Contract 模板 | done_when.yaml（v2，以 AC 为单位）；模板 = 同类需求复用的 AC 骨架 |
| R001（评估者与执行者隔离） | sdlc 的信息隔离：实现子 agent 看不到评审判据；验收在独立会话 |
| R002（闸门资产只能人签） | sdlc 的 G2（判据冻结 lock_done_when.py sign --by <人>）与 G3（例外复核） |
| 变更提案 / G2 签字（sdlc） / change proposal / G2 signing (sdlc) / NEEDS_HUMAN | assets/change_proposal.md 变更提案 + G2/G3 人签；账本 ledger.md 记 propose |
verify_g1 / review_g2（qanat 的机器闸 / 评审闸） |
sdlc L7 的 A 档机械验收 / C 档判断验收——注意与 sdlc 的 G1（世界裁决）、G2（判据冻结）不是同一对门 |
| MemoryAsset（eval_case / rubric_version / failure_memory） | 归档目录 specs/<slug>/ 里的测试集 / 评判 rubric；failure_memory = ledger.md 的 fail 行 + escape-defects.md |
| daemon / 运行时 | 本地测试与 CI；/sdlc 的 acceptance 阶段 |
calibration.resolved 事件 |
G3 记录里"标准不清"的改判（g3_record.md） |
The gap (why "write some tests" is not a compiler)
A composite of three atoms: Judgment (which line a clause belongs on — its decidability), Capability (the three emitters: fitness-fn config, eval_case battery, judge program), and Knowledge (the disciplines: Assured 3-filter, ACH mutation-guided generation, PBT sub-layer, PAJAMA program form).
The load-bearing reason this is not free:
What ships with it
11 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.
- assets/compile_manifest.yaml 3.8 KB
- assets/decisions_template.md 1.4 KB
- eval/fixtures/manifest_bad_up.yaml 1.4 KB
- eval/fixtures/manifest_good.yaml 1.4 KB
- eval/gate.json 2.9 KB
- eval/report.md 2.4 KB
- references/anti_patterns.md 3.3 KB
- references/behavioral-line.md 3.3 KB
- references/decidability-ladder.md 4.8 KB
- references/judgment-line.md 3.2 KB
- scripts/verify_compile.py 6.8 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 · 242 lines · 342 tokens per session scan A b23682ab0dd5
spec-compile is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed yesterday), licensed MIT. It adds 342 tokens to every session and 4,642 once invoked, about $0.0017 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 2026-09-05.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.