Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/samibs/skillfoundrynpx agentmods add skills/samibs/skillfoundry/replayWrote 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/samibs/skillfoundry/replay)<a href="https://agentmods.dev/skills/samibs/skillfoundry/replay"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/replay.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 89 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00010 | $0.02190 |
| Opus 5 | $0.00005 | $0.01095 |
| Sonnet 5 | $0.00002 | $0.00438 |
| Haiku 4.5 | $0.00001 | $0.00219 |
Grade A, and why
replay 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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/replay - Replay & Session Viewer
Re-run the last
/goor/forgeexecution, or view past session timelines.
Usage
/replay Replay the last execution
/replay --dry-run Show what would be replayed without executing
/replay --from=<phase> Resume from a specific phase (ignite, forge, temper, inspect, remember)
/replay --failed Replay only failed stories
/replay --show List recent sessions and display timeline
/replay --show <id> Show specific session timeline (by ID or index)
Instructions
You are the Replay Manager. When /replay is invoked, re-run the last execution pipeline or display past session timelines.
When invoked with --show (Session Viewer):
This is a read-only view of past agent sessions. No re-execution occurs.
-
List sessions (no session ID given):
./scripts/session-recorder.sh listDisplay recent sessions in a table:
Session History ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ # Session ID Agent Story Outcome 1 20260215_143000_a1b2c3d4 coder STORY-003 success 2 20260215_120000_e5f6g7h8 tester STORY-002 success 3 20260214_160000_i9j0k1l2 fixer STORY-001 failed -
Show session timeline (session ID or index given):
./scripts/session-recorder.sh show <session-id>Display the full session timeline:
Session Timeline — 20260215_143000_a1b2c3d4 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Agent: coder | Story: STORY-003 | Duration: 12m 34s 14:30:00 ▶ SESSION START 14:30:15 📁 READ src/auth/types.ts 14:31:02 📁 CREATE src/auth/jwt.ts 14:32:18 🔧 EVENT Running tests — 12 test files 14:33:45 💡 DECISION Used RS256 for JWT signing Why: Asymmetric keys allow public key verification Alternatives: HS256 (shared secret risk), ES256 (less support) Confidence: 0.9 14:35:22 📁 MODIFY src/auth/index.ts 14:38:10 🔧 EVENT Anvil Tier 3 passed 14:42:34 ✅ SESSION END — success (anvil-pass) Summary: Events: 4 | Decisions: 1 | Files: 3 (1 read, 1 created, 1 modified)
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.
- 4d ago First seen · 273 lines · 10 tokens per session scan A b83025df04a0
replay is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 2,190 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
bug-fix
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.
forge-troubleshoot
Diagnose and resolve Plan Forge issues — failed runs, broken validation gates, misconfigured environments, stalled slices, and orchestrator errors. Use when a plan run fails or the forge behaves unexpectedly.
health-check
Run a full Plan Forge health diagnostic — environment, setup validation, and completeness scan. Use to verify your forge is properly configured and code is clean.
audit-loop
Run a recursive audit drain loop — discover findings from the running system, triage each into bug/spec/classifier lanes, repeat until convergence. USE FOR: end-to-end audit of a deployed or locally-running app, draining findings to zero. DO NOT USE FOR: single-shot tempering runs (use forgetemperingrun), one-off bug…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.