メニュー
Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/boshu2/agentops --skill codebase-reconコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".
Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".
Initialize minimal AgentOps documentation and verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".
SKILL.md を表示中
| name | codebase-recon |
| description | Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon". |
| practices | ["legacy-code-seams","ddd-bounded-context","design-by-contract"] |
| hexagonal_role | supporting |
| consumes | ["repo-context","existing-docs"] |
| produces | ["codebase-recon.v1","evidence-bounded-recon-report"] |
| context_rel | [{"kind":"customer-of","with":"research"},{"kind":"customer-of","with":"validate"},{"kind":"customer-of","with":"doc"}] |
| skill_api_version | 1 |
| user-invocable | true |
| context | {"window":"fork","intent":{"mode":"task"},"sections":{"exclude":["HISTORY"]},"intel_scope":"topic"} |
| metadata | {"capabilities":["codebase_recon"],"effects":["write_recon_pack"],"canonical_status":"canonical","disposition":"keep_specialist","tier":"execution","dependencies":[]} |
| output_contract | codebase-recon.v1 JSON validated by skills/codebase-recon/scripts/validate-output.sh with a companion cited report |
Build a reusable, falsifiable model of a repository. This skill reports what the tree and executable probes support; it does not edit code or issue a final PASS/WARN/FAIL verdict.
One skill replaces a cluster of loose recon skills. Steer it with mode, view emphasis, lens, and depth — do not invent a second skill for each shape.
| Control | Values | Use when |
|---|---|---|
| Mode | baseline | delta | First pack vs refresh after a prior recon |
| View emphasis | mental model · bounded audit · pattern evidence · synthesis | Archaeology-style map, audit-style findings, pattern harvest, or executive synthesis |
| Lens | persistence · auth · CLI · build · test (one per pass) | Domain-deep cut instead of a shallow whole-tree sweep |
| Depth | quick · standard · deep | Orientation vs onboarding vs decision-grade evidence |
Ask for the shape explicitly, for example:
codebase-recon --mode=delta --view=audit --lens=cli --depth=standard
codebase-recon baseline, mental-model view, persistence lens, deep
Natural-language equivalents count. The durable pack still carries all four
views; emphasis changes what you spend tokens on and what the companion report
leads with. Pattern packaging beyond evidence pointers belongs in
pattern-mining. Binding PASS/FAIL stays with
validate.
baseline mode. If one exists, verify its
still-valid claims against the current commit and use delta mode. Preserve
valid evidence by reference and describe only changed paths and synthesis.fact, inference, or unknown,
assign confidence, and cite evidence for facts and inferences.Enter through what the repository declares about itself — README, architecture
docs, build manifests, CLI help — and only then verify those declarations
against the tree. Before the first broad search, list the declared entry points
and trace at least one of them to code. The named failure mode is grep-first
drift: opening with keyword sweeps builds a model of whatever happened to
match, and the recon inherits the search terms' blind spots instead of the
repository's actual shape. When declaration and code disagree, that is a
finding, not noise: record the doc's claim as inference, the traced behavior
as fact, and cite both.
Each pass adopts exactly one lens — persistence, auth, CLI surface, build system, test harness — and follows it from entry point through domain logic to its tests before switching lenses. A pass ends in exactly one of two states: the lens has one complete entry-to-test flow, or the report names the file and line where the trace was cut and why. The named failure mode is the shallow sweep: touching every directory at depth one produces a file inventory that reads like a model but supports no claim, because no path was followed far enough to falsify anything.
The durable output doc earns its keep only if a future reader can re-verify a
claim without redoing the recon. Every fact cites file:line; every
inference cites the file:line facts it rests on. A claim that cannot be
cited is downgraded to unknown before the report ships — never shipped
uncited at its original confidence. The manifest validator accepts a bare file
path (it requires the path resolve to an existing regular file, so a bare
directory is rejected as a coverage gap), but does not require the line number;
hold the companion report to the stricter floor: a path without a line is a
pointer to homework, not a citation, and counts as a coverage gap in the
report's own terms.
When reconstructing a repository other than the one that ships this skill, pass
--repo-root <target> to the validator so evidence resolves against the target
tree rather than the skill's own checkout.
.agents/scratch/codebase-recon/<run-id>/codebase-recon.json with companion report
codebase-recon.md in the same directory.codebase-recon.v1 JSON manifest plus an evidence-cited Markdown
report covering the same commit, mode, flows, claims, and scope boundaries.skills/codebase-recon/scripts/validate-output.sh <codebase-recon.json>
validates the machine-readable manifest; the cited Markdown report remains
its human-readable companion.Baseline manifests carry at least one complete entry-to-test flow. Delta
manifests name an existing prior recon, prove baseline_verified: true, and
describe at least one changed path. Every manifest lists both inspected and
uninspected scope.
The validator is the machine boundary:
skills/codebase-recon/scripts/validate-output.sh <recon.json>
Evidence entries are existing file paths, optionally followed by a line number.
Delta manifests require an existing prior pack, baseline_verified: true, and
at least one described change.
Executable behavior: references/codebase-recon.feature.