replen 1.0.23 → 1.0.24

package/dist/discover-projects.js

@@ -171,7 +171,7 @@ export function discoverProjects(roots) {
             seenGithub.add(githubFullName);
             // Slug + display name both anchor on the GitHub repo NAME, not the
             // local folder name. Deriving from the folder meant a folder rename (or
-            // an org rename like Covelent→nsokin) minted a fresh slug and the server
+            // an org rename) minted a fresh slug and the server
             // inserted a duplicate row. `~/code/drone` with remote
             // `nsokin/palisade-website` now registers as slug `palisade-website`.
             // The repo name is also the fallback display name, so a generic

package/extras/skills/replen/SKILL.md

@@ -353,7 +353,13 @@ verdict it calibrates the relevance floor for this project, and your
 adopt/skip pattern continuously tunes the ranking via the taste vector).
 A skip coded `modality-collision` teaches Replen that this repo fits a
 *different* modality — so it stays available for the right project but stops
-colliding with this one.
+colliding with this one. A skip coded `covered` is the strongest signal you
+can send: it tells Replen the capability is **already built in this repo**, so
+it stops probing that facet entirely and won't surface a different tool for it
+next session. Use `covered` ONLY when you've confirmed the implementation in
+the code (e.g. the repo has its own `services/llm_client.py`), not just because
+a similar dependency exists — that's what makes "we already do this" stick to
+the capability instead of replaying every session against a new candidate.
 
 **Candidate's README is unreachable (WebFetch 404)**. Note it in the
 writeup (`Caveats: README unreachable; verdict based on description

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "replen",
-  "version": "1.0.23",
+  "version": "1.0.24",
   "description": "Make your AI coding tools smarter. One command, no API keys, free. Replen watches what your projects actually do and surfaces a few things worth bringing in each month. Use one as is, port a piece of another, cherry pick an idea, or build it clean room. The match happens inside your AI tool's session. A few actionable matches a month, by design.",
   "type": "module",
   "bin": {