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 shashankreddy509/claude-tdd-kit --skill condense-feedbackgit clone --depth 1 https://github.com/shashankreddy509/claude-tdd-kitWrote 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/shashankreddy509/claude-tdd-kit/condense-feedback)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/condense-feedback"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/condense-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/condense-feedback"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/condense-feedback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.02038 |
| Opus 5 | $0.00049 | $0.01019 |
| Sonnet 5 | $0.00020 | $0.00408 |
| Haiku 4.5 | $0.00010 | $0.00204 |
Grade A, and why
condense-feedback 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 9d ago.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
condense-feedback
Shrink a grown feedback or memory file in place. Lossless-by-meaning: every distinct lesson survives, only the repetition dies.
This is the counterpart to merge-feedback. That skill only ever GROWS a file (append a
dated section, never delete, superset-checked). This one is the only thing allowed to
shrink it — deliberately separate, because deciding "these two bullets are the same
lesson" is a judgment call that can silently lose something, so it is gated behind an
explicit invocation and a backup.
Argument: a path to the file. No argument → default to tasks/feedback.md in the
current repo (what merge-feedback writes). If that does not exist, ASK which file rather
than guessing — this skill rewrites files, and a wrong target is destructive.
When to use
- The file has many near-duplicate entries on the same theme after a long run of sessions.
- The user says "too big", "minimize it but keep all the content", "compress this memory file".
- A memory index is approaching a read limit and needs to fit.
NOT for summarization. This is lossless-by-meaning compression. A future session must be able to avoid every mistake the original file recorded.
Core rule
Preserve every distinct lesson; only repetition dies. Merge points that mean the same thing, drop the narrative retelling, but never delete a unique rule, a unique gotcha, a concrete constant, or a cross-reference.
The test for a merge: two bullets merge only if a future session would take the same action from either one. Similar wording is not the same lesson — "verify a merge from the API" and "verify a deploy by hashing the served bytes" look alike and are different rules. When unsure, keep both. A file that is 5% larger than ideal costs nothing; a dropped lesson costs the mistake it was written to prevent.
Steps
1. Resolve SKILL_DIR, then back up and measure FIRST
Set SKILL_DIR to the absolute path of the directory containing THIS SKILL.md you just
Read — your harness reported that path in the Read result. The script is always a direct
sibling of this file, in every install layout:
What ships with it
1 file 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.
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.
- 9d ago First seen · 167 lines · 99 tokens per session scan A 4ee65c54a69b
condense-feedback is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 17d ago), licensed MIT. It adds 99 tokens to every session and 2,038 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
codebase-memory-mcp
Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches. Use when a user mentions codebase memory MCP, searchgraph, tracepath, indexrepository, worktree indexes, or oversized graph caches.
project-memory
Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.
memory-hygiene
Keep agent-written memory files from rotting. Audits /.claude/projects/ /memory/ for facts the tree now contradicts — stale version pins, passed sequence facts, vanished paths — plus MEMORY.md index drift, and enforces the memory format contract at write time. Use when the user says "audit my memory", "memory is…
learn-on-failure
Save a learning to project memory. Invoke automatically (without the user asking) whenever a task required more than one fix cycle to resolve — e.g. a test failed and needed a second attempt, a compile error required a correction, an API behaved unexpectedly, or an assumption proved wrong mid-task. Also invoke when…