instructionsMode: "owned" causes repo upgrade/repo init to fully overwrite the tool's instructions file on every run -- no managed-section markers, no preservation of surrounding content, no warning, no backup. This already affects two built-in integrations today, not just custom tools: Cursor (.cursor/rules/swamp.mdc) and Kiro (.kiro/steering/swamp-rules.md) are both hardcoded to "owned", so any hand-edits to those specific files are destroyed on the next upgrade. Claude and OpenCode/Codex/Copilot get the safer "shared" mode (managed section, migrates legacy unmarked content instead of destroying it, preserves everything else) purely because their instructions filenames happen to match a hardcoded 4-name allowlist (AGENTS.md, AGENT.md, CLAUDE.md, CONVENTIONS.md).

For custom tools via swamp agent setup, the mode is derived silently from that same allowlist check against whatever filename the user types -- there is no prompt, no flag, and no way to select "shared" mode for a custom filename through the wizard. The wizard's own completion summary only annotates the safe case (Instructions: foo.md (shared)) -- when the destructive "owned" mode is selected, the summary says nothing at all, so a user has no way to know their file will be fully overwritten on every future upgrade unless they separately run swamp agent list and notice the Mode: owned line, or read the source.

Verified directly against the latest published source (v20260711.232311.0-sha.6bda08e7, confirmed to be both the tip of main and the version this report's environment has installed): manually editing .swamp-custom-tools.yaml to change instructionsMode: owned to instructionsMode: shared for a non-allowlisted filename works and is honored by repo upgrade -- the field is validated only against the two literal string values, not re-derived against the filename allowlist. So the safe behavior is fully functional today; it's just undiscoverable without reading source.

Proposed solution

Have the wizard explicitly ask whether the target file may already contain content worth preserving (it already offers to scan an existing repo for detection -- this is the natural place to also ask), and offer "shared" as a real, presented choice regardless of filename, rather than deriving it silently from a hardcoded list.
When "owned" is selected (by the wizard or by filename derivation), say so explicitly in the completion summary and in agent list output -- e.g. "Instructions: foo.md (owned -- this file will be fully overwritten on every repo upgrade)".
Document instructionsMode in the shipped skill materials: what the two values mean, and that "shared" is usable for any instructions filename via .swamp-custom-tools.yaml, not just the four built-in allowlisted names.
Consider changing the built-in Cursor and Kiro configs to "shared" mode as well, matching the other four built-in tools, since "shared" mode already handles the "file has legacy content with no markers" migration case gracefully.

Alternatives considered

Adding a blanket confirmation prompt before any overwrite -- rejected as noisy for the common case (a genuinely fresh repo with no pre-existing content), where scanning already tells the wizard there's nothing to protect. The better fix is making the existing detection-and-choice machinery (which already exists for the scan-an-existing-repo step) also drive the mode decision, rather than adding friction uniformly.

02Bog Flow

Shipped

7/13/2026, 5:53:58 PM

Click a lifecycle step above to view its details.

03Sludge Pulse

stack72 assigned stack727/13/2026, 3:13:17 PM

stack72 commented 7/13/2026, 5:54:10 PM

Thanks @jeremy for reporting this! The fix has been merged and a release is on its way. We appreciate your contribution to swamp.

Bundled extension model cannot deserialize AWS SDK S3 XML that works in direct Deno

gcp/sheets spreadsheets-values: batch_get crashes with "Request with GET/HEAD method cannot have body"

Token creation API and UI scope selector for collective tokens (phase 4 of #960)

Make Cloudflare CRUD methods factory-aware so list-discovered resources can be managed in-place

Add @swamp/kubernetes/statefulset model type

serve: workflow.approvals and workflow.run.search still full-scan the workflow-run store after the #1284 data.query pushdown

Sync guard skips bound namespace directory during push — 0 files pushed after namespace migrate

Flaky #1052 preparePush test: mtime-granularity race on Linux tmpfs

command/shell renders JSON-object stdout lines as the literal string 'undefined'

Issue redactor treats the MongoDB authSource parameter as a secret, corrupting reproduction steps

namespace unset --migrate silently deletes artifact history via catalog-rebuild GC (~484k files lost)

Docs: document repo root resolution from subdirectories

Expose the swamp.club feed as an RSS feed

Email invitation is not linked to account created from invite URL

Add serve, datastore, vault, and worker wildcard scopes to token registry (phase 4 prep, #960)

datastore setup extension drops 'namespace' from --config, making extensions that require it impossible to configure

Docs: update manual to document --yes/-y as the standard confirmation-skip flag

Docs: update data.query and CEL expressions references for SQL pushdown

Docs: document collective token CLI usage in API key authentication pages

Add a --release-notes option to `swamp update` (or even make it the default)

Docs: manual should state workflow unknown keys are rejected and placement is step-only (follow-up to #1240)

Make GCP CRUD methods factory-aware so list-discovered resources can be managed in-place

serve: read ops (data.query, workflow.approvals, workflow run.search) linearly scan the whole datastore — ~350–600ms floor regardless of match count

Running "swamp workflow run ..." in a subdir of the swamp repo fails

Guide agents to inspect reports after failed model and workflow runs

serve: main JS thread holds ~40–70% of a core while idle (no clients, no runs, --no-schedule)

Search box collapses to near-zero width on mobile on the Extensions page

Extensions page: Search bar missing on mobile

spreadsheets-values: every method fails with 'Missing required path parameter: spreadsheetId' — implementation reads a global argument the schema does not declare

namespace migrate/set workflow broken for extension datastores: migrate skipped by sync guard, set not idempotent, migrate-index empties shards

ExtensionInfo.latestVersion typed 'string' but registry returns null; harden pull/resolve for prerelease-only extensions

workflow.run: relay a custom model method's output as method_output (command steps already do)

promptChoice infinite-loops on non-interactive stdin

gcp _lib: unconditional x-goog-user-project header causes USER_PROJECT_DENIED (403) for service accounts without the serviceUsageConsumer role

extension push: issue-verdict review is indistinguishable from missing/stale

swamp extension version crashes with 'Invalid CalVer version: "null"' when only a prerelease (beta/rc) version is published

Pushing an extension after creating a public git repo that is the same as other previously pushed extensions doesn't update the "Verified public repository"

`datastore setup filesystem` never transfers content when leaving a sync-based (remote) datastore — copies only the catalog and hardcodes `filesPulled: 0`

Scaleway models: create methods should not require the resource ID they generate (ipId/gatewayId/serverId/...)

gcp/calendar events.list reads wrong array field ('defaultReminders' not 'items') → always returns 0 events

provisioner.provision fails with 'Cannot read properties of undefined (reading trim)' at method_execution_service.ts:852

method_execution_service.ts:852 crashes on undefined.trim() when writeResource receives undefined instance name

CLI support for collective API tokens (phase 3 of #960)

@swamp/gcp/calendar: service-account & ADC auth mint cloud-platform-scoped tokens → 403 on Calendar API

Scope enforcement and whoami introspection for collective tokens (phase 2 of #960)

fix(software-factory): DeclaredSchemaSchema.enum rejects boolean literals

Surface cloud-provider labels (scaleway, digitalocean, oracle/oci) as first-class search/filter facets on the Extensions page

Profile link in genesis subdirectory does not navigate back to main profile

Profile stats: per-user daily rollup table + MV in ClickHouse

Reconcile collective-token CLI activity to members (attribute → bonus → stamp → even-split)

Telemetry stats consumer: unsanitized subcommand in Mongo update path drops user metrics silently

Telemetry stats consumer: insert_id dedup commits before the write it guards — any upsert failure is silently swallowed on retry

Job-level labels: block is silently ignored, not rejected

Issue submission redactor silently corrupts report bodies

CLI telemetry: fold third-level verbs into subcommand + canonicalize aliases

Docs: update extension info reference to document extensions (type grafts) in content metadata

Docs: swamp skill repo-structure reference still documents repo-local .swamp/telemetry/ as live

Add safe adoption and lifecycle methods for existing Hetzner resources

Docs: update manual telemetry reference for user-global spool and telemetry.yaml opt-out

export const extension can graft methods onto foreign-collective types, undisclosed in extension info / contentMetadata

Add lookup support to the Cloudflare DNS records model

Expand token scope registry to full taxonomy (phase 1 addendum, #960)

Docs: document user-global telemetry (telemetry.yaml opt-out, spool location, telemetry stats behavior)

score_daily rollup strands stale grains when a day-less grant re-stamps onto a later day

swamp-club: global rate limiter runs pre-auth and collapses all direct clients into one per-IP bucket — 429s authenticated CLI traffic

Collective API token scopes: domain, persistence, and auth threading (phase 1 of #960)

Telemetry migration from ~/.swamp/telemetry should auto-detect home-as-repo

feed_post_score_events queue grows unboundedly (no TTL, no delete-on-delivery)

Issue-filing skill should require ownership classification before submitting a bug

Interactive finder silently drops the preview pane on narrower terminals, and layout selection is unstable

@-mention autocomplete for users when writing lab ripples

Remove comments from /feed and redesign the page

Interactive finder preview corrupts: overlapping/stale lines when preview content overflows the pane

Score-refresh consumer: harden coalescing against a diverse backlog (bistability)

Remove feed comments — consolidate discussion in Discord

Add a 'my collective extensions' filter to extensions page

Relax the profanity filter

Extension search returns edit-distance noise for short queries ("asdl" → "AWS DEADLINE")

Telemetry recoverOrphaned startup race with multiple replicas (created_at-based)

Telemetry retry/failed path has the same non-atomic claim as #820

Grant revoke is never applied to the running server — under `--grant-reload auto` and `manual` alike, a revoked grant stays in force until an explicit `access reload`