failure-containment-review
Skill1.7k starsChanged 8 days agoApache-2.0View on GitHub
Review Lody PRs or local lifecycle and sync changes for failure-containment regressions and disproportionate owner/facade machinery. Use for changes to release, teardown, retry, fencing, readiness, transport or store-cache ownership.
Trending
More talk lately.about the whole repository
Who's talking about LodyAI/Lody
- LodyAI/acp-extension-codex“feat: expose native session archives through Lody Core”GitHub · Nov 3, 2026 · 1 reactions
- LodyAI/acp-extension-core“feat: define reversible session archive capabilities”GitHub · Nov 3, 2026 · 1 reactions
- Asuka109/Lody“feat: download oversized remote session files in ranges”GitHub · Oct 15, 2026 · 1 reactions
- LodyAI/acp-extension-codex“perf: defer ACP validation schema construction”GitHub · Nov 4, 2026
- LodyAI/acp-extension-claude“feat: expose explicit title-marker archive capabilities”GitHub · Nov 3, 2026
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub (50 times).
On GitHub · 50
- Nov 3, 2026feat: expose native session archives through Lody Core — LodyAI/acp-extension-codex1 reaction · 1 comment
- Nov 3, 2026feat: define reversible session archive capabilities — LodyAI/acp-extension-core1 reaction · 1 comment
- Oct 15, 2026feat: download oversized remote session files in ranges — Asuka109/Lody1 reaction · 2 comments
- Nov 4, 2026perf: defer ACP validation schema construction — LodyAI/acp-extension-codex0 reactions
- Nov 3, 2026feat: expose explicit title-marker archive capabilities — LodyAI/acp-extension-claude0 reactions · 3 comments
45 more on GitHub
- Nov 1, 2026fix: upgrade bundled Claude Code to 2.1.316 — LodyAI/acp-extension-claude0 reactions
- Oct 28, 2026fix: fork Pi sessions at completed native boundaries — LodyAI/acp-extension-pi0 reactions
- Oct 24, 2026Update DimCode icon to the 45:32 brand mark — agentclientprotocol/registry0 reactions
- Oct 22, 2026fix(cli): preserve interrupted turn outcome after restart — delete-cloud/Lody0 reactions
- Oct 22, 2026fix: prevent recursive Git transport wrapper targets — delete-cloud/Lody0 reactions
- Oct 18, 2026fix: report Claude quota failures at native turn boundaries — LodyAI/acp-extension-claude0 reactions
- Oct 17, 2026fix: preserve causal order when user history syncs late — delete-cloud/Lody0 reactions
- Oct 12, 2026fix: configure official extension and toolbar icons — wibus-wee/lody-wxt0 reactions
- Oct 11, 2026fix: trace Live Activity registration and lifecycle — innei-dev/lody-ios0 reactions · 2 comments
- Oct 10, 2026fix: delegate automatic session titles to ACP clients — LodyAI/acp-extension-codex0 reactions
- Oct 10, 2026fix: preserve official DeepSeek Messages endpoints — LodyAI/acp-extension-dsh0 reactions
- Oct 9, 2026feat: implement Core controls on Harness 0.2.0-rc.2 — LodyAI/acp-extension-dsh0 reactions
- Oct 8, 2026fix: support inline prompts after /plan — LodyAI/acp-extension-codex0 reactions
- Oct 7, 2026[BUG] RTCPeerConnection.close() does not cancel or join in-flight ICE/TURN gathering — shinyoshiaki/werift-webrtc0 reactions
- Oct 6, 2026feat: support ACP session forks at native turn boundaries — LodyAI/acp-extension-dsh0 reactions
- Oct 4, 2026feat: allow overriding the Pi binary via LODY_PI_PATH — LodyAI/acp-extension-pi0 reactions · 2 comments
- Sep 26, 2026feat: stream normalized Codex subagent events — LodyAI/acp-extension-codex0 reactions
- Sep 26, 2026feat: define normalized subagent event contract — LodyAI/acp-extension-core0 reactions
- Sep 24, 2026feat: generate native Kimi ACP session titles — LodyAI/acp-extension-kimi0 reactions
- Sep 24, 2026feat: use native Harness session titles — LodyAI/acp-extension-dsh0 reactions
- Sep 24, 2026feat: advertise and tag native session titles — LodyAI/acp-extension-grok0 reactions
- Sep 24, 2026feat: advertise automatic session title capability — LodyAI/acp-extension-codex0 reactions
- Sep 24, 2026feat: advertise and tag automatic session titles — LodyAI/acp-extension-claude0 reactions
- Sep 24, 2026feat: declare automatic session title capability — LodyAI/acp-extension-core0 reactions
- Sep 24, 2026fix(chat): keep slash menu off URLs and paths — ThinkInAIXYZ/deepchat0 reactions · 1 comment
- Sep 23, 2026fix: expose Harness tool calls and results through ACP — LodyAI/acp-extension-dsh0 reactions
- Sep 23, 2026[BUG] URL 或路径中的斜杠误触发命令补全,导致 Enter 无法发送消息 — ThinkInAIXYZ/deepchat0 reactions · 1 comment
- Sep 21, 2026fix(acp): display submitted plans in client plan cards — LodyAI/acp-extension-kimi0 reactions
- Sep 20, 2026fix: preserve missing-file semantics for ACP Plan mode — LodyAI/acp-extension-kimi0 reactions
- Sep 20, 2026feat: discover and explicitly enable installed Pi extensions — LodyAI/acp-extension-pi0 reactions · 1 comment
- Sep 13, 2026test: await usage accounting test completion — LodyAI/acp-extension-core0 reactions
- Sep 13, 2026fix: kimi usage accounting review findings — LodyAI/acp-extension-kimi0 reactions
- Sep 13, 2026fix: claude usage accounting review findings — LodyAI/acp-extension-claude0 reactions
- Sep 13, 2026fix: codex usage accounting review findings — LodyAI/acp-extension-codex0 reactions
- Sep 13, 2026feat: report DSH token usage and DeepSeek USD estimates — LodyAI/acp-extension-dsh0 reactions
- Sep 13, 2026fix: accumulate Grok prompt usage with correction deltas — LodyAI/acp-extension-grok0 reactions
- Sep 10, 2026OSS 功能对齐 — innei-dev/lody-ios0 reactions · 1 comment
- Sep 9, 2026test: match review completion to the requested turn — LodyAI/acp-extension-codex0 reactions
- Sep 9, 2026feat: define worktree project identity — LodyAI/acp-extension-core0 reactions
- Sep 9, 2026fix: await settings profile smoke tests — LodyAI/acp-extension-dsh0 reactions
- Sep 8, 2026fix: bridge Grok plan approval through ACP — LodyAI/acp-extension-grok0 reactions
- Sep 8, 2026feat: decouple ACP plan mode from permissions — LodyAI/acp-extension-kimi0 reactions
- Sep 7, 2026fix: preserve ACP v1 prompt across goal continuations — LodyAI/acp-extension-codex0 reactions
- Sep 7, 2026[Request]: Lody — ScoopInstaller/Extras0 reactions
- Sep 6, 2026fix: seed Grok session permission flags like the TUI — LodyAI/acp-extension-grok0 reactions
In this repository14 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- .agents/docs/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .agents/notes/AGENTS.mdAGENTS.md
- e2e/AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- site-docs/AGENTS.mdAGENTS.md
- specs/AGENTS.mdAGENTS.md
- archive-agent-notesSkill
- effect-tsSkill
- effect-v3-to-v4Skill
- lody-cliSkill
- lody-loro-sync-stackSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Use the requested base; these examples assume origin/main.
- Distinctive: line 34
If the base is unavailable, state the limit rather than inventing a comparison.
- Distinctive: line 38
Search the diff, not the whole tree, for changed failure semantics:
- Distinctive: line 65
Follow the callers upward until you reach a top-level owner: workspace dispose, application quit, a request handler, a UI acquire, or a CLI …
- Distinctive: line 142
Do not flag strictness already present on the base or complexity without a concrete failure or maintenance cost.
- Distinctive: line 149
When dispatching another agent, send this prompt with the placeholders filled in:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Failure-containment review
Find changes that make one owner stricter at the cost of everything around it.
The rules are in failure containment; this
skill is the procedure. Repository review rules still decide what gets reported:
read the root AGENTS.md and
.github/codex-review.md first.
1. Fix the comparison
Record the reviewed revision or working-tree snapshot and the comparison base.
Use the requested base; these examples assume origin/main. Read the base version
of each cited file. A path already strict on the base is not a new regression.
For a PR, resolve its head and merge base:
gh pr view <PR> --json headRefOid,baseRefName,files
git fetch origin pull/<PR>/head:pr-<PR>
REVIEW_HEAD=$(git rev-parse pr-<PR>)
BASE=$(git merge-base "$REVIEW_HEAD" origin/main)Without a PR, use the local branch and git merge-base HEAD origin/main (or the
requested base). For uncommitted work, record git status --short and inspect
staged, unstaged and relevant untracked files. git diff "$BASE" -- covers tracked
working-tree changes; read new files separately without staging them. Cite local
paths/lines as a working-tree snapshot, not as a commit that lacks those changes.
If the base is unavailable, state the limit rather than inventing a comparison.
2. Collect candidates
Search the diff, not the whole tree, for changed failure semantics:
git diff "$BASE" "$REVIEW_HEAD" -U0 -- 'apps/*/src' 'packages/*/src' | rg -n \
-e '^-.*\.catch\(\(\) =>' -e '^-.*catch \{' -e 'allSettled' -e 'AggregateError' \
-e 'retain|fence|retir|failure[s]?\b' -e 'Promise\.reject\(' \
-e 'dispose|destroy|release|close|unload|teardown' \
-e 'timeoutMs|syncRoom|waitFor|handoff|confirm|receipt'For working-tree review omit "$REVIEW_HEAD", include the task's actual paths
(including guidance/skills when those are the change), and inspect untracked files.
Then classify each hit:
- Removed tolerance. A
.catch(() => {}),try/catchorallSettledaround cleanup was removed or narrowed, or a cleanup now throws. - New fence. Retained state or repeated cleanup failure makes later callers reject. Automatic retry can still fence a resource under persistent failure.
- New gate. A new
awaiton sync, confirmation, readiness or a peer receipt sits before an action that previously ran directly. - New accumulation. An array or map gains failures or owners and has no bound.
- Strict facade. A compatibility method now propagates failures that its old implementation swallowed or logged.
3. Trace each candidate to the top
Follow the callers upward until you reach a top-level owner: workspace dispose, application quit, a request handler, a UI acquire, or a CLI command. At each frame record what the frame does when the call rejects. Look in particular for:
- a later step in the same sequence that no longer runs;
- a later destroy that removes recovery state during its owned recovery budget, or a terminal flush failure silently reported as saved;
- retained recovery without a named longer-lived owner or retention/retry bounds, a second Repo on the same database, or shutdown that cannot finish under quota failure;
- a memoized promise (
disposePromise,closeReceipt) that caches the rejection and turns a partial teardown into a permanent one; - a key whose only retry path needs the operation that the fence blocks, which is a deadlock in practice;
- a gate that runs on startup, periodic or forced paths as well as on the racy one.
- background or React cleanup callers that use
voidwithout observing rejection; - concurrent acquires that duplicate cleanup instead of joining one in-flight retry;
- degraded gate results written into success caches, once sets or pending-write ACKs.
4. Test realism and the claimed hazard
Name the concrete trigger: IndexedDB quota or a closed database, SQLite busy, a network drop during flush or close, an absent local peer, or a timeout. If an ordinary environmental failure triggers the path, it is not a hypothetical edge case under the review rules.
Then establish what the owner below actually guarantees after partial failure. Shared reference counting alone does not prove durable data or safe reuse. Inspect the relevant implementation and behavioral evidence when available; if it is not, mark the claim conditional and name the missing verification. For authors, the default is to preserve base behavior and record that condition in the owning Note. Missing evidence alone justifies neither a new fence nor destructive cleanup; investigate before changing the contract. Do not claim that the base is verified safe.
Distinguish awaited failure delivery from background observation, and independent cleanup from destruction of recovery dependencies within their chosen lifetime. At quit, sign-out or workspace deletion, check a bounded final flush, user-visible reporting of unconfirmed persistence and resource release; persistent failure must not prevent termination. A waiter deadline alone does not stop raw writes. Cross-dispose recovery is optional: require a named longer-lived owner, bounded retention/retry, and same-key acquire adopting the retained Repo or joining its confirmed close before replacement. Never require an ownerless retry loop or a second Repo on the same database. For gates, verify that unconfirmed/degraded results remain observable and retryable rather than becoming authoritative answers.
5. Proportion pass
- For each new exported Service, Layer or helper, search for consumers outside its own module and tests. An export with none is speculative.
- For each new implementation, check whether the one it replaces still exists. An old implementation kept only for a type import is dead code.
- In a facade, look for maps or flags that mirror state the native owner already holds. Look for two places that decide the same status.
- Compare the size of the change with the migration sizing guide, and name the independent units that could ship separately.
6. Report
Rank findings by impact. For each one, give:
file:lineat the reviewed commit or working-tree snapshot;- the chain: realistic trigger → propagation through callers → user-visible effect;
- the base behavior it replaces;
- the smallest fix consistent with verified ownership, such as continuing independent cleanup with bounded recovery or terminal finalization, sharing cleanup retry without blocking safe reuse, observing background failure, or returning an explicit unconfirmed result without caching it;
- whether the finding is verified in the code or conditional on unverified library behavior.
Under the GitHub Code Review bar, report only P0/P1. An ordinary failure that now skips independent cleanup, prevents verified safe reuse or gates unrelated work can meet P1; assess the actual user impact. Necessary exclusion of unsafe overlap is not itself a containment regression. Proportion findings are not P0/P1 on their own; include them only in design reviews that ask for them.
Do not flag strictness already present on the base or complexity without a concrete failure or maintenance cost. An automatic retry or deadline alone is not an exemption: assess progress under persistent failures, shared retry, caller error observation and whether degraded results poison authoritative state.
Delegation prompt
When dispatching another agent, send this prompt with the placeholders filled in:
Review <PR or branch> in the Lody repository against base <base>. Use the
failure-containment-review skill (.agents/skills/failure-containment-review/SKILL.md)
and the rules in .agents/docs/failure-containment.md.
Look for changes that buy local correctness or predictability with system
stability: cleanup failures that now abort teardown, retained failures that
permanently block a key, new waits or confirmations in front of work that did not
need them, unbounded failure buffers, and compatibility facades that became
stricter than their old callers expected. Then do the proportion pass: exports
with no consumer, superseded code kept alive, and facade state duplicating the
owner.
For every finding, verify the lower owner's partial-release/reuse guarantees and
trace a realistic trigger through callers to user-visible effects. Distinguish
independent cleanup from dependent destruction, awaited from background release,
and authoritative from unconfirmed gate results. Check bounded terminal shutdown
and named recovery ownership with same-Repo adoption on reacquire. Compare with the base and propose
the smallest safe fix. For local changes include staged, unstaged and task-relevant
untracked files. Cite the reviewed snapshot; mark unverified assumptions conditional.
Do not edit files.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

