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 end-sessiongit 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/end-session)<a href="https://agentmods.dev/skills/shashankreddy509/claude-tdd-kit/end-session"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/end-session/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/end-session"><img src="https://agentmods.dev/badge/skills/shashankreddy509/claude-tdd-kit/end-session.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 | $0.00061 | $0.03127 |
| Opus 5 | $0.00030 | $0.01563 |
| Sonnet 5 | $0.00012 | $0.00625 |
| Haiku 4.5 | $0.00006 | $0.00313 |
Grade C, and why
end-session scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s --max-time 2 "${TASK_INBOX_URL:-http://localhost:8765}/api/todos" | python3 -c "import json,sys; [print(t['text']) for t in json.load(sys.stdin)['todos'] if not t.get('done')]" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 2 "${TASK_INBOX_URL:-http://localhost:8765}/api/todos" >/dev/null && echo up || echo down How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End Session
Read the entire conversation from this session. Extract and synthesize everything the user revealed about how they want to work.
Output — four artifacts
tasks/feedback.md— DELEGATE to themerge-feedbackskill. Invoke it. It owns the synthesis of this session's preferences/corrections into the five sections and the never-delete / superset merge rules (with its own SUPERSET-CHECK). Do NOT reimplement that merge logic here — call the skill. (This is the single source of truth for the feedback merge, shared with start-session's auto-capture.)- The project memory vault — update the persistent memory for the current project, never a
hardcoded path. Derive the path from cwd: replace every
/with-, write under~/.claude/projects/<that-slug>/memory/(create if absent). One durable fact per file with frontmatter + a one-lineMEMORY.mdpointer. Merge, don't replace: read the existing file first, preserve prior facts, only correct one if this session proved it wrong (and say so). Save only durable, non-obvious facts — not what git/the repo records, and not behavioral preferences (those go to feedback viamerge-feedback). tasks/session-notes.md— the 2-line "Left off" note (see below).- Optional task inbox — if a local task-inbox service is running, first propose CLOSING the points this session finished (user confirms; never auto-close), then push this session's remaining unfinished points, so they reach a daily brief / phone instead of dying in a session-notes file nobody opens. Close before adding — adding first pollutes the list you then scan. Skipped silently when no such service is running (see below).
session-notes.md detail
The "Left off" note is exactly two lines describing where work stopped, so the next /start-session
can resume cleanly (it reads this file):
- <the task that was mid-progress when the session ended>
- <the next concrete step to take>
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 · 212 lines · 0 tokens per session scan C d7c5ea6cceb0
end-session is a skill published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 16d ago), licensed MIT. It adds 61 tokens to every session and 3,127 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…