SpecStory is a local-first tool that records and indexes conversations with AI coding assistants so developers can search, reuse, and share their solutions. It is for preserving coding decisions, snippets, and other knowledge across projects and development tools. Its catalogue skills and commands process saved sessions into reusable agent skills and connect the workflow to coding agents.
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.
git clone --depth 1 https://github.com/specstoryai/getspecstoryWrote 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/commands/specstoryai/getspecstory/pr-review)<a href="https://agentmods.dev/commands/specstoryai/getspecstory/pr-review"><img src="https://agentmods.dev/badge/commands/specstoryai/getspecstory/pr-review/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/commands/specstoryai/getspecstory/pr-review"><img src="https://agentmods.dev/badge/commands/specstoryai/getspecstory/pr-review.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 | $0.00007 | $0.00959 |
| Opus 5 | $0.00003 | $0.00479 |
| Sonnet 5 | $0.00001 | $0.00192 |
| Haiku 4.5 | $0.00001 | $0.00096 |
Grade A, and why
pr-review 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 10d 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.
This is a copy
91% identical to code-review — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current pull request status: !
gh pr view $1 - Current pull request diff: !
gh pr diff $1
Your task
Examine pull request $1 using the GitHub CLI command.
Ignore any changes to:
- .specstory/history files
- .claude/ files
- .cursor/ files
- ./specstory binary
- CLAUDE.md
- AGENT.md
- changelog.md
Please code review the pull request.
Review line by line and explain to me the purpose of each change. Use file names and line numbers to reference the changes, but also sequentially number every observation so we can easily reference them.
In the line by line review, pay attention to:
- clarity of variable names
- Go lang idiomatic code
- code clarity and simplicity, readable over clever
- "why" comments, not "how" comments
- missing comments
- missing log output
- missing analytics tracking
- single function exit point where possible (immediate guard clauses are OK)
- goroutines tracked by a
sync.WaitGroupusewg.Go(func() { ... }), neverwg.Add(1)paired with adefer wg.Done()— flag anyAdd/Donepair, especially one where theDonesits in a different function from itsAdd - verify the code has to exist, is actually needed, and is in use
- verify the code is DRY, and doesn't replicate the same or similar code
- for test cases, ensure a data-driven approach is being used rather than lots of repetitive test code
Format your line by line review like this example:
cmd/remote.go
Line 12 (removed): Removed unused import of pkg/service package
- (1) ✅ Good - Cleaning up unused imports is proper Go hygiene
Lines 157-162 (modified): Changed from loading config directly to using RPC client
// Old: config, err := service.LoadConfig(dir)
// New: rpcClient, err := client.NewRPCClient(dir)
- (2) ✅ Good architectural decision - Now operates via daemon RPC instead of direct file access
- (3) ✅ Proper defer cleanup pattern for RPC client
- (4) ✅ Variable name rpcClient is clear and follows conventions
Lines 164-189 (new): Added remote status check before disabling
- (5) ✅ Good UX - Detects current connection state to provide better feedback
- (6) ✅ Type assertions use the two-value form (ok pattern) for safety
- (7) ⚠️ Nested if statements become deeply indented (4 levels) - could be refactored for readability
- (8) ✅ Variable names wasConnected, oldURL are descriptive
- (9) ❓ Missing error handling - if remote.status call fails, we continue anyway. Should we?
---
pkg/remote/sync.go
Lines 260-265 (modified): Success messages now come after RPC call
- (10) ✅ Comment "config is now saved" is helpful context
- (11) ⚠️ Misleading comment placement - comment says "config is now saved" but we can't be certain from this code's perspective (that happens in the daemon)
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.
- 10d ago First seen · 82 lines · 7 tokens per session scan A 15ffb5c58061
pr-review is a command published in the GitHub repository specstoryai/getspecstory (1,325 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 959 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to code-review, differing in 14 lines, and is treated as a copy.
Other commands, from other repositories
test-tools
Systematic smoke tests for Backseat Driver tools - validates core functionality and basic error handling after tool updates.
url
Scrape and integrate documentation from provided URLs using Firecrawl tools.
package
Look up library documentation using Context7 MCP tools for a specific task.
octo-deliver
Delivery phase - Review, validate, and test with multi-AI quality assurance.
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-status
Show structured SDD status for an active change.